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. 11-RESID-POST-AA
    6. 79796
    Prev
    Next
    INDEX
    Explanations

    temperature

    np_max-act · gemini-2.0-flash

    cases related to medical conditions.

    oai_token-act-pair · gpt-4o-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
    rx
    -0.07
    .cv
    -0.07
    敷
    -0.06
    ัตถ
    -0.06
     Rp
    -0.06
    眠
    -0.06
     Apr
    -0.06
     Sketch
    -0.06
     vacancy
    -0.06
    _oct
    -0.06
    POSITIVE LOGITS
     也
    0.07
    ался
    0.07
     전쟁
    0.06
    SocketAddress
    0.06
     geldi
    0.06
    -total
    0.06
    _die
    0.06
    벨
    0.06
     sym
    0.06
    (nums
    0.06
    Activations Density 0.002%

    No Known Activations