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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 56941
    Prev
    Next
    INDEX
    Explanations

    Company listings

    np_max-act · gemini-2.0-flash

    The neuron flags phrases pointing to additional or related services or businesses (e.g. “other related …,” “related businesses,” “other related information”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elders
    -0.06
    /widget
    -0.06
    ье
    -0.06
     beads
    -0.06
    .Fat
    -0.06
    _itr
    -0.06
    _sales
    -0.06
    _Log
    -0.06
    hos
    -0.06
    _sigma
    -0.06
    POSITIVE LOGITS
    ],[-
    0.07
     XPAR
    0.06
     Modelo
    0.06
     область
    0.06
     виде
    0.06
     uğra
    0.06
    .)↵↵↵↵
    0.06
     оформ
    0.06
     Pek
    0.06
     @{$
    0.06
    Activations Density 0.034%

    No Known Activations