© 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
    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. 130105
    Prev
    Next
    INDEX
    Explanations

    Weather news

    np_max-act · gemini-2.0-flash

    The neuron flags special conversational boundary tokens (like turn delimiters and speaker labels).

    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
    مح
    -0.07
    dirs
    -0.07
    土
    -0.07
    سط
    -0.06
    Mos
    -0.06
    마다
    -0.06
     Maria
    -0.06
    map
    -0.06
    thumb
    -0.06
    better
    -0.06
    POSITIVE LOGITS
     GENERAL
    0.07
    GENERAL
    0.07
     HOLD
    0.06
     Rt
    0.06
     PUBLIC
    0.06
    .tm
    0.06
     Starts
    0.06
    .args
    0.06
     nomin
    0.06
     Beam
    0.06
    Activations Density 0.042%

    No Known Activations