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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 44310
    Prev
    Next
    INDEX
    Explanations

    programming constructs and function definitions in code

    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
    using
    -0.10
    iglia
    -0.07
    mPid
    -0.07
    _HERSHEY
    -0.07
    OPSIS
    -0.07
    actionDate
    -0.06
    auga
    -0.06
    REDIENT
    -0.06
    ahoma
    -0.06
    ROLLER
    -0.06
    POSITIVE LOGITS
    output
    0.13
    plugin
    0.13
    default
    0.13
    attribute
    0.13
    override
    0.13
    instance
    0.12
    endpoint
    0.12
    executable
    0.12
    metadata
    0.12
    readonly
    0.12
    Activations Density 4.623%

    No Known Activations