© 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. 94784
    Prev
    Next
    INDEX
    Explanations

    quarter

    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
    ип
    -0.07
     Helena
    -0.07
     deposit
    -0.07
     provoke
    -0.07
     плен
    -0.07
     longstanding
    -0.07
     smoking
    -0.06
     shed
    -0.06
     shuttle
    -0.06
    Driving
    -0.06
    POSITIVE LOGITS
    .Try
    0.06
    ListNode
    0.06
    thickness
    0.06
     ninete
    0.06
    ());
    ↵
    ↵
    0.06
     VERY
    0.06
    lásil
    0.06
    .createStatement
    0.06
     }];↵↵
    0.06
    ');");↵
    0.05
    Activations Density 0.015%

    No Known Activations