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. 9742
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
     öncelik
    -0.06
     Vid
    -0.06
    -ok
    -0.06
    Spoiler
    -0.06
     Streams
    -0.06
     Rin
    -0.06
    Nit
    -0.06
    、↵
    -0.06
    ">
    ↵
    ↵
    -0.05
    zens
    -0.05
    POSITIVE LOGITS
    .Style
    0.08
    _mm
    0.07
     Expires
    0.07
     Stocks
    0.07
     headquartered
    0.07
     MT
    0.07
     stash
    0.07
     emb
    0.06
     Disconnect
    0.06
     meetings
    0.06
    Activations Density 0.002%

    No Known Activations