© 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. 19-RESID-POST-AA
    6. 73678
    Prev
    Next
    INDEX
    Explanations

    RC models

    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
     Teresa
    -0.08
    Tour
    -0.07
    _KEY
    -0.07
     tape
    -0.07
     Coordinator
    -0.07
    ,string
    -0.07
     Valve
    -0.06
     Suddenly
    -0.06
    ın
    -0.06
    _surf
    -0.06
    POSITIVE LOGITS
     xmm
    0.06
    .ShouldBe
    0.06
     �
    0.06
    ~
    0.06
    手を
    0.06
    ¸
    0.06
     испыт
    0.06
     oversight
    0.06
    ,No
    0.06
     adap
    0.06
    Activations Density 0.032%

    No Known Activations