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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96083
    Prev
    Next
    INDEX
    Explanations

    patterned or structural elements within the text, particularly related to formatting or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elli
    -0.06
    elas
    -0.06
     GAP
    -0.06
    efs
    -0.06
    ugins
    -0.06
    elia
    -0.06
     ELF
    -0.06
    /path
    -0.06
    .si
    -0.06
     вÑĭÑıв
    -0.05
    POSITIVE LOGITS
    .Apis
    0.07
    Scalars
    0.07
     Reserve
    0.06
    ael
    0.06
    scp
    0.06
     Quad
    0.06
    bidden
    0.06
    ockets
    0.06
     condemning
    0.06
    uent
    0.06
    Activations Density 0.003%

    No Known Activations