© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 30594
    Prev
    Next
    INDEX
    Explanations

    encyclopedia

    np_max-act · gemini-2.0-flash

    Wikipedia-style section headings, especially multi-item noun phrases joined by commas and “and.”

    oai_token-act-pair · gpt-5Triggered 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
    IX
    -0.07
    амет
    -0.07
    EHICLE
    -0.06
    SIDE
    -0.06
    BOVE
    -0.06
    Night
    -0.06
     Avery
    -0.06
     causal
    -0.06
     evenings
    -0.06
    ERE
    -0.06
    POSITIVE LOGITS
     obchod
    0.08
     �
    0.07
    ंगल
    0.07
    Brandon
    0.06
     inability
    0.06
    _POSITION
    0.06
     restless
    0.06
     TypeInfo
    0.06
    .Ap
    0.06
    �s
    0.06
    Activations Density 0.108%

    No Known Activations