© 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. 28851
    Prev
    Next
    INDEX
    Explanations

    notable titles, ranks, or categories associated with individuals

    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
    klad
    -0.08
    ajs
    -0.07
    grave
    -0.07
    ekk
    -0.07
    Aligned
    -0.07
    unga
    -0.07
    folk
    -0.07
    lew
    -0.07
    _VENDOR
    -0.07
    modo
    -0.07
    POSITIVE LOGITS
    autiful
    0.07
    aires
    0.07
     Haram
    0.06
    ÌĢ
    0.06
     Strand
    0.06
    /top
    0.05
    uxe
    0.05
     Sacr
    0.05
    ARGER
    0.05
    Ìģ
    0.05
    Activations Density 0.001%

    No Known Activations