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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68861
    Prev
    Next
    INDEX
    Explanations

    -share

    np_max-act · gemini-2.0-flash

    This neuron detects the “share” token in URL parameters (e.g., in UTM or social share links).

    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
     AppMethodBeat
    -0.07
    ��
    -0.06
    WithTag
    -0.06
    랍
    -0.06
    Liquid
    -0.06
     Ann
    -0.06
     :)↵↵
    -0.06
    ISTIC
    -0.06
    任
    -0.06
    인증
    -0.06
    POSITIVE LOGITS
     Μαρ
    0.07
     ovarian
    0.07
     osm
    0.06
    azar
    0.06
     teen
    0.06
     obraz
    0.06
    меж
    0.06
    -share
    0.06
    ières
    0.06
    384
    0.06
    Activations Density 0.000%

    No Known Activations