© 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. 40714
    Prev
    Next
    INDEX
    Explanations

    references to news articles and the associated press or reporting bodies

    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
    positor
    -0.07
    ê¹
    -0.06
    emon
    -0.06
    ua
    -0.06
    ameron
    -0.06
    lam
    -0.06
    ifu
    -0.06
    posit
    -0.05
    odash
    -0.05
    ifar
    -0.05
    POSITIVE LOGITS
    UMB
    0.07
     Zub
    0.07
    /etc
    0.07
     quán
    0.06
    alist
    0.06
    atism
    0.06
    ldb
    0.06
     Ùħز
    0.06
    åľ
    0.06
    SETTING
    0.06
    Activations Density 0.003%

    No Known Activations