Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 28854
    Prev
    Next
    INDEX
    Explanations

    closed-form solutions

    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
    63
    -0.06
    말
    -0.06
    Forum
    -0.06
    ]:
    ↵
    -0.06
    ZO
    -0.06
    ithub
    -0.06
    appropriate
    -0.06
     little
    -0.06
     PARTICULAR
    -0.06
    �y
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Toe
    0.07
    =N
    0.07
    latesAutoresizingMaskIntoConstraints
    0.06
    .digest
    0.06
    ži
    0.06
     поддерж
    0.06
    _OD
    0.06
     inspirational
    0.06
     deviceId
    0.06
    Activations Density 0.087%

    No Known Activations