© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60719
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure cues

    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
    .conv
    -0.07
    _UNDEFINED
    -0.07
    ISC
    -0.06
    illon
    -0.06
    hea
    -0.06
    ystal
    -0.06
    hek
    -0.06
     Lazy
    -0.06
     ark
    -0.06
     Tel
    -0.06
    POSITIVE LOGITS
    INGLE
    0.07
    dings
    0.07
    .AF
    0.06
    aned
    0.06
    urus
    0.06
     McGr
    0.06
    (mut
    0.06
    ingle
    0.06
    .@
    0.06
    893
    0.06
    Activations Density 0.009%

    No Known Activations