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. 99576
    Prev
    Next
    INDEX
    Explanations

    error messages/code

    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
    _HOUR
    -0.07
    �로
    -0.07
    .square
    -0.07
    collapse
    -0.06
    Những
    -0.06
    _resources
    -0.06
     puntos
    -0.06
    亮
    -0.06
    选择
    -0.06
     látky
    -0.06
    POSITIVE LOGITS
     abdominal
    0.07
    returned
    0.06
     Places
    0.06
    VML
    0.06
    pagesize
    0.06
    _optional
    0.06
    hdr
    0.06
    iew
    0.06
     Seb
    0.06
     Signals
    0.06
    Activations Density 0.030%

    No Known Activations