© 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. 93653
    Prev
    Next
    INDEX
    Explanations

    elements related to measurements and dimensions

    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
    evin
    -0.08
     PATCH
    -0.07
    Cab
    -0.07
    ActionCreators
    -0.07
    krit
    -0.07
    åĶ¯
    -0.07
    662
    -0.07
    tro
    -0.06
     mux
    -0.06
    PATCH
    -0.06
    POSITIVE LOGITS
     Valley
    0.06
    -sur
    0.06
     Wheeler
    0.06
    anka
    0.06
    okino
    0.06
    Äįné
    0.06
     Rise
    0.06
    itos
    0.06
    ëŁī
    0.06
    vla
    0.06
    Activations Density 0.059%

    No Known Activations