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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 80609
    Prev
    Next
    INDEX
    Explanations

    Conversational, subjective language

    np_max-act · gemini-2.0-flash

    words that express negation or comparison/contrast (e.g., "n't", "than", comparative markers).

    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
     sailor
    -0.07
     пром
    -0.06
    ویزی
    -0.06
     Hit
    -0.06
    avana
    -0.06
    tips
    -0.06
    Collapse
    -0.06
    Perl
    -0.06
    альному
    -0.05
    ROWN
    -0.05
    POSITIVE LOGITS
    _notifier
    0.07
     enterprise
    0.07
     الوقت
    0.07
    (cp
    0.06
     ^=
    0.06
    (IC
    0.06
    _attention
    0.06
     apis
    0.06
    ,R
    0.06
     neu
    0.06
    Activations Density 0.216%

    No Known Activations