© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74800
    Prev
    Next
    INDEX
    Explanations

    -radius

    np_max-act · gemini-2.0-flash

    The neuron never fires for any of these inputs—it’s effectively a “dead” neuron that matches nothing.

    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
     boot
    -0.06
    _ACTIVE
    -0.06
     Sig
    -0.06
     WM
    -0.06
     meat
    -0.05
     apo
    -0.05
     Call
    -0.05
     プ
    -0.05
    Compact
    -0.05
    ..."
    -0.05
    POSITIVE LOGITS
    -radius
    0.08
     borderRadius
    0.07
     mimo
    0.07
    [char
    0.07
    Radius
    0.07
    .cornerRadius
    0.07
    δώ
    0.06
    ‌ی
    0.06
    аніт
    0.06
    ENCIES
    0.06
    Activations Density 0.001%

    No Known Activations