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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12549
    Prev
    Next
    INDEX
    Explanations

    bias

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens referring to the model’s own internal biases or limitations (e.g. “biases,” “limitations,” “underlying algorithms”).

    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
     welfare
    -0.07
     lump
    -0.07
    .dark
    -0.07
     méně
    -0.06
    internet
    -0.06
    υκ
    -0.06
    863
    -0.06
     жал
    -0.06
    umped
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     biases
    0.08
    (wx
    0.07
    //
    ↵
    0.07
     BE
    0.06
     bias
    0.06
    .param
    0.06
    _ti
    0.06
    ViewHolder
    0.06
     voj
    0.06
    .sn
    0.06
    Activations Density 0.005%

    No Known Activations