© 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. 57139
    Prev
    Next
    INDEX
    Explanations

    numerical data and sequences

    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
    asco
    -0.08
    Apis
    -0.08
    abra
    -0.07
     ï½
    -0.07
    abee
    -0.07
    /*č↵
    -0.07
     pij
    -0.07
    ---</
    -0.07
    canf
    -0.07
    835
    -0.07
    POSITIVE LOGITS
    NE
    0.06
     LINEAR
    0.06
    .argument
    0.05
    space
    0.05
    ÃŃg
    0.05
     Revel
    0.05
     Powered
    0.05
    0.05
    _variation
    0.05
    swing
    0.05
    Activations Density 0.004%

    No Known Activations