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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106198
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "log" 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
    staking
    -0.07
    urous
    -0.07
    clin
    -0.06
    atoire
    -0.06
    optera
    -0.06
    çois
    -0.06
    egot
    -0.06
    odate
    -0.06
    aters
    -0.06
    álido
    -0.06
    POSITIVE LOGITS
    gers
    0.09
    gings
    0.08
    arith
    0.08
    -log
    0.08
    /log
    0.08
    istical
    0.08
    sd
    0.08
    istically
    0.07
    istics
    0.07
    itech
    0.07
    Activations Density 0.012%

    No Known Activations