© 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. 94000
    Prev
    Next
    INDEX
    Explanations

    terms related to academic publishing and ethical guidelines

    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
    è«
    -0.07
     im
    -0.06
    imer
    -0.06
    609
    -0.06
    onds
    -0.06
    å¹ħ
    -0.06
     iht
    -0.06
    iors
    -0.06
     Glas
    -0.06
    _rs
    -0.06
    POSITIVE LOGITS
    -blind
    0.08
    opaque
    0.07
    blind
    0.07
    afen
    0.07
    hazi
    0.07
     blinds
    0.07
     blind
    0.07
     DropIndex
    0.07
    tach
    0.06
    лиÑĤ
    0.06
    Activations Density 0.004%

    No Known Activations