© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 49971
    Prev
    Next
    INDEX
    Explanations

    BASIS

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jim
    -0.06
    _PLL
    -0.06
    .aw
    -0.06
     wild
    -0.06
     __("
    -0.06
    >;
    -0.06
     yere
    -0.06
     UIApplication
    -0.05
     headaches
    -0.05
    	row
    -0.05
    POSITIVE LOGITS
     BASIS
    0.10
    视频
    0.07
     керів
    0.07
    Radi
    0.07
    -base
    0.07
    _basis
    0.06
    hexdigest
    0.06
    通
    0.06
     mapStateToProps
    0.06
    たち
    0.06
    Activations Density 0.001%

    No Known Activations