© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9061
    Prev
    Next
    INDEX
    Explanations

    -top

    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
     einz
    -0.07
    grams
    -0.06
    icates
    -0.06
    �
    -0.06
    érer
    -0.06
    disable
    -0.06
    _fd
    -0.06
    _topic
    -0.06
     �
    -0.06
    ť
    -0.06
    POSITIVE LOGITS
    ACHE
    0.07
    时
    0.07
     العربية
    0.07
    ाट
    0.07
     Nội
    0.07
     Ukr
    0.07
     hát
    0.06
     Asphalt
    0.06
     Eston
    0.06
    .uc
    0.06
    Activations Density 0.004%

    No Known Activations