© 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. 84146
    Prev
    Next
    INDEX
    Explanations

    names of individuals and entities in the text

    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
    adil
    -0.07
    ikat
    -0.07
    ijkstra
    -0.07
    íĦ¸
    -0.07
    ystal
    -0.07
    chy
    -0.07
    ãģŁãĤī
    -0.07
     è¡ĮæĶ¿
    -0.07
    ROLS
    -0.07
    awi
    -0.07
    POSITIVE LOGITS
     whose
    0.12
     who
    0.10
    whose
    0.09
     whom
    0.08
     plus
    0.08
    who
    0.07
     which
    0.07
     (
    0.07
     as
    0.06
     also
    0.06
    Activations Density 0.023%

    No Known Activations