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. 19-RESID-POST-AA
    6. 91680
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    three
    -0.06
    [contains
    -0.06
    젝트
    -0.06
    364
    -0.06
     �
    -0.06
    <Any
    -0.06
    Navigator
    -0.06
    merged
    -0.06
     strange
    -0.06
    _gate
    -0.06
    POSITIVE LOGITS
    íše
    0.07
     evasion
    0.07
    ipi
    0.07
    IFORM
    0.06
    (UINT
    0.06
    .Tags
    0.06
    ashi
    0.06
     Extraction
    0.06
     reacts
    0.06
     outbound
    0.06
    Activations Density 0.010%

    No Known Activations