© 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. 118887
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" in different contexts

    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
    idget
    -0.07
    bery
    -0.07
    enstein
    -0.07
    룡
    -0.07
    алÑİ
    -0.07
    slashes
    -0.07
    dorf
    -0.07
    him
    -0.07
    ermal
    -0.07
    еÑĢжав
    -0.06
    POSITIVE LOGITS
     least
    0.11
    /by
    0.11
    tempts
    0.10
    -risk
    0.09
    lassian
    0.09
    elier
    0.08
    rophy
    0.08
     once
    0.08
    /on
    0.08
    -home
    0.07
    Activations Density 0.281%

    No Known Activations