Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 91581
    Prev
    Next
    INDEX
    Explanations

    flexibility and adaptability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -election
    -0.07
    @include
    -0.07
     speech
    -0.07
     Law
    -0.07
     substantially
    -0.06
    Courtesy
    -0.06
     Speech
    -0.06
    -d
    -0.06
    -b
    -0.06
     vis
    -0.06
    POSITIVE LOGITS
    Dataset
    0.07
     chois
    0.06
    ैट
    0.06
    ARDS
    0.06
    овий
    0.06
    _make
    0.06
    駅徒歩
    0.06
     어머니
    0.06
    浪
    0.06
    anking
    0.06
    Activations Density 0.045%

    No Known Activations