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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 83499
    Prev
    Next
    INDEX
    Explanations

    digitalWrite

    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
     kiểm
    -0.07
    )reader
    -0.07
    озем
    -0.06
    ]).
    -0.06
     los
    -0.06
     زاد
    -0.06
     hinge
    -0.06
     mixes
    -0.06
    ']?></
    -0.06
    _DEC
    -0.06
    POSITIVE LOGITS
    postal
    0.07
     reboot
    0.07
    Moved
    0.07
     IC
    0.06
     TITLE
    0.06
    lift
    0.06
    draft
    0.06
     scrutin
    0.06
    bear
    0.06
    �
    0.06
    Activations Density 0.000%

    No Known Activations