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. 23-RESID-POST-AA
    6. 40600
    Prev
    Next
    INDEX
    Explanations

    Random snippets of text

    np_max-act-logits · gemini-2.0-flash

    future

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    हर
    -0.07
     attitude
    -0.07
     trabajo
    -0.06
    ughters
    -0.06
     =>↵
    -0.06
     estimator
    -0.06
     Hello
    -0.06
    �
    -0.06
    =}
    -0.06
     مض
    -0.06
    POSITIVE LOGITS
     excerpt
    0.06
    xAA
    0.06
    lng
    0.06
    aupt
    0.06
     "!
    0.06
    //****************************************************************************
    0.06
    rike
    0.06
    ContainerGap
    0.06
    .Warning
    0.06
    arsi
    0.06
    Activations Density 0.963%

    No Known Activations