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. 30962
    Prev
    Next
    INDEX
    Explanations

    rejuvenate

    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
    asına
    -0.07
    败
    -0.06
     hull
    -0.06
    eyes
    -0.06
    事
    -0.06
     swarm
    -0.06
     mir
    -0.06
     Scope
    -0.06
    -child
    -0.06
    来
    -0.06
    POSITIVE LOGITS
     c
    0.07
     nour
    0.07
    '
    ↵
    ↵
    0.07
     antidepress
    0.07
     rejuven
    0.07
    <=$
    0.06
    ']]↵
    0.06
    =sc
    0.06
     refuse
    0.06
     DOWNLOAD
    0.06
    Activations Density 0.012%

    No Known Activations