© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 32608
    Prev
    Next
    INDEX
    Explanations

    elial

    np_max-act · gemini-2.0-flash
    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
    -j
    -0.07
    ("================
    -0.07
    -ed
    -0.07
    pto
    -0.07
    _cached
    -0.06
    markt
    -0.06
     frightened
    -0.06
    	speed
    -0.06
    ——
    -0.06
    っていた
    -0.06
    POSITIVE LOGITS
    als
    0.07
    elial
    0.07
    ΣΤ
    0.06
    λοι
    0.06
    engl
    0.06
    виг
    0.06
     OFFSET
    0.06
     مؤس
    0.06
    WillAppear
    0.06
     retrie
    0.06
    Activations Density 0.002%

    No Known Activations