© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130101
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    tokens marking the start of an assistant reply (i.e., the assistant turn/message boundary).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _signal
    -0.07
    okino
    -0.07
    enabled
    -0.07
    -processing
    -0.07
    114
    -0.06
    initial
    -0.06
    Description
    -0.06
     icmp
    -0.06
     MPEG
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    бом
    0.07
     Europa
    0.06
     curb
    0.06
     Tax
    0.06
     tax
    0.06
     ödem
    0.06
     verm
    0.06
     куст
    0.06
     деньги
    0.06
    에서도
    0.06
    Activations Density 0.306%

    No Known Activations