© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 14064
    Prev
    Next
    INDEX
    Explanations

    related

    np_max-act · gemini-2.0-flash

    The neuron fires on the section headers that label related or recommended content in an article (e.g. the “Related”/“Related Content” block).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    promotional information related to fundraising events or charitable activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SELL
    -0.07
    .SDK
    -0.07
    now
    -0.06
     MUCH
    -0.06
    \/\/
    -0.06
    (FALSE
    -0.06
    NESS
    -0.06
    _IA
    -0.06
    ��
    -0.06
    érience
    -0.06
    POSITIVE LOGITS
    andaş
    0.08
     teknoloj
    0.07
    capture
    0.06
     Background
    0.06
     exists
    0.06
     збір
    0.06
     bluetooth
    0.06
     chảy
    0.06
     evaluating
    0.06
     exist
    0.06
    Activations Density 0.003%

    No Known Activations