© 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. 29690
    Prev
    Next
    INDEX
    Explanations

    indicators of publication details and timestamps

    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
    vey
    -0.07
     con
    -0.06
    3
    -0.06
    2
    -0.06
    4
    -0.06
    Ñĩин
    -0.06
     sil
    -0.06
     silk
    -0.05
    rega
    -0.05
    CSR
    -0.05
    POSITIVE LOGITS
    MLE
    0.08
    ardware
    0.08
    hton
    0.08
    ãĤ¤ãĥ³ãĥĪ
    0.07
    otionEvent
    0.07
    /lg
    0.07
    ToBounds
    0.07
    inox
    0.07
    ransition
    0.07
    BootApplication
    0.07
    Activations Density 0.002%

    No Known Activations