© 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. 30951
    Prev
    Next
    INDEX
    Explanations

    search results

    np_max-act · gemini-2.0-flash

    This neuron detects words referring to the retrieval context or metadata (e.g. “returned,” “google,” “snippet,” “Wikipedia”).

    oai_token-act-pair · o4-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
     cornerback
    -0.07
     defense
    -0.07
     butto
    -0.07
     builders
    -0.07
     probably
    -0.07
     jeopard
    -0.06
     explore
    -0.06
     negativity
    -0.06
     �
    -0.06
     tracks
    -0.06
    POSITIVE LOGITS
    -The
    0.06
    なの
    0.06
    .fillStyle
    0.06
     withObject
    0.06
    上げ
    0.06
     noss
    0.06
    στο
    0.06
    .ForEach
    0.06
    (PORT
    0.06
     сай
    0.06
    Activations Density 0.003%

    No Known Activations