© 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. 118896
    Prev
    Next
    INDEX
    Explanations

    references to procedural actions and processes in various contexts

    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
     mes
    -0.07
     Mes
    -0.06
     mez
    -0.06
    ç§ij
    -0.06
    ãĥ¼ãĥ¬
    -0.06
    ercul
    -0.06
    kud
    -0.06
    FetchRequest
    -0.06
    YST
    -0.06
    IVEN
    -0.06
    POSITIVE LOGITS
    astically
    0.09
    ologically
    0.07
     rather
    0.07
    avad
    0.07
    >\<^
    0.06
    íķĺëĤĺ
    0.06
    NaN
    0.06
    rather
    0.06
    ÙIJÙĩ
    0.06
     essentially
    0.06
    Activations Density 0.039%

    No Known Activations