© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 83945
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Negative Logits
    _P
    -0.07
     klub
    -0.07
    _BEFORE
    -0.07
     hip
    -0.07
    Empresa
    -0.07
    apia
    -0.06
    Flexible
    -0.06
     inspir
    -0.06
    _DP
    -0.06
    _smart
    -0.06
    POSITIVE LOGITS
    EditingController
    0.06
    ournemouth
    0.06
    ;",
    0.06
    قات
    0.06
    ahun
    0.06
     rais
    0.06
    _RANGE
    0.06
     hallway
    0.06
    AntiForgeryToken
    0.06
     crossAxisAlignment
    0.06
    Activations Density 0.030%

    No Known Activations