© 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. 126799
    Prev
    Next
    INDEX
    Explanations

    descriptors of geographical features and locations

    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
     finally
    -0.08
    ylie
    -0.07
     ultimately
    -0.07
    _-_
    -0.07
    ullet
    -0.07
     reportedly
    -0.07
     increasingly
    -0.06
     eventually
    -0.06
    rend
    -0.06
     cul
    -0.06
    POSITIVE LOGITS
     naturally
    0.10
     Naturally
    0.09
    kea
    0.07
    yer
    0.07
     natürlich
    0.06
     ê·¸ëŁ°
    0.06
    boo
    0.06
    .setResult
    0.06
    bard
    0.06
     Rin
    0.06
    Activations Density 0.057%

    No Known Activations