© 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. 3950
    Prev
    Next
    INDEX
    Explanations

    actions or phrases indicating movement or positioning

    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
    sic
    -0.07
    eum
    -0.06
    ettes
    -0.06
    sons
    -0.06
     denn
    -0.06
    graphics
    -0.06
    वत
    -0.06
    ffa
    -0.06
    illions
    -0.06
    jis
    -0.06
    POSITIVE LOGITS
    ASN
    0.07
    CPP
    0.06
    sert
    0.06
    ahir
    0.06
    wards
    0.06
    ãģĹãģı
    0.06
    spender
    0.06
    oksen
    0.06
    iner
    0.06
    enda
    0.06
    Activations Density 0.059%

    No Known Activations