© 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. 93475
    Prev
    Next
    INDEX
    Explanations

    occurrences of the definite article "the"

    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
    krom
    -0.07
    kola
    -0.07
    ndata
    -0.07
    ryo
    -0.06
    ç¢
    -0.06
    ahan
    -0.06
     поб
    -0.06
    .ERR
    -0.06
    ugo
    -0.06
    ãĤ«ãĥĨ
    -0.06
    POSITIVE LOGITS
    veis
    0.07
     course
    0.07
     process
    0.07
    itaire
    0.06
    åĽ£
    0.06
    odel
    0.06
    359
    0.06
    hin
    0.06
    302
    0.06
    ombre
    0.06
    Activations Density 0.020%

    No Known Activations