© 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. 19-RESID-POST-AA
    6. 118961
    Prev
    Next
    INDEX
    Explanations

    .

    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
    .SH
    -0.06
    ]=='
    -0.06
     popularity
    -0.06
    notEmpty
    -0.05
     Crescent
    -0.05
     island
    -0.05
     woes
    -0.05
    -ring
    -0.05
    Unload
    -0.05
    $string
    -0.05
    POSITIVE LOGITS
     gases
    0.07
     Exercise
    0.07
    _batch
    0.06
    Environmental
    0.06
     ambitious
    0.06
     Courses
    0.06
     sends
    0.06
    寶
    0.06
    plates
    0.06
     desks
    0.06
    Activations Density 0.000%

    No Known Activations