Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73354
    Prev
    Next
    INDEX
    Explanations

    Quoted or written text

    np_max-act · gemini-2.0-flash

    tokens that indicate document structure or formatting (code/config blocks, headers/metadata and other layout/formatting elements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Writable
    -0.07
    resident
    -0.07
     youngster
    -0.07
     invariant
    -0.07
    vergence
    -0.06
     denomination
    -0.06
    Cha
    -0.06
     příjem
    -0.06
    ukes
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     samt
    0.07
     广
    0.07
    使用
    0.07
    어나
    0.06
     conceded
    0.06
     біл
    0.06
    Votes
    0.06
    _coef
    0.06
     overst
    0.06
     musí
    0.06
    Activations Density 0.211%

    No Known Activations