© 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. 15-LLAMASCOPE-RES-131K
    11. 103740
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "book" and its variations

    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
    ors
    -0.08
    utom
    -0.07
    enne
    -0.07
    est
    -0.07
    گاÙĩ
    -0.07
    MENT
    -0.07
    ugs
    -0.06
    rib
    -0.06
    254
    -0.06
    738
    -0.06
    POSITIVE LOGITS
    ç±į
    0.12
    shelf
    0.10
    worm
    0.10
    keeping
    0.10
    stores
    0.09
    ends
    0.09
    ellers
    0.09
    eller
    0.09
    -length
    0.08
    stagram
    0.08
    Activations Density 0.049%

    No Known Activations