© 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. 15-RESID-POST-AA
    6. 79148
    Prev
    Next
    INDEX
    Explanations

    old

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proporcion
    -0.08
    EHICLE
    -0.07
     swims
    -0.07
     бух
    -0.07
    ocations
    -0.07
    Navig
    -0.07
    azione
    -0.07
     literacy
    -0.07
    successfully
    -0.07
    jection
    -0.07
    POSITIVE LOGITS
     old
    0.16
     Old
    0.15
    Old
    0.12
     OLD
    0.10
     oldest
    0.09
    .old
    0.09
    -old
    0.09
    _old
    0.09
     oldValue
    0.08
     Βα
    0.08
    Activations Density 0.024%

    No Known Activations