© 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. 106975
    Prev
    Next
    INDEX
    Explanations

    instances of collective action or collaboration

    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
    .cf
    -0.06
    arc
    -0.06
    aze
    -0.06
    äºĴ
    -0.06
    å¢ĥ
    -0.06
     audience
    -0.06
     Garcia
    -0.06
    atcher
    -0.05
    alles
    -0.05
    454
    -0.05
    POSITIVE LOGITS
     others
    0.10
     forces
    0.09
     effort
    0.08
     efforts
    0.08
    others
    0.07
     Others
    0.07
     chorus
    0.07
    Others
    0.07
    aro
    0.06
    bras
    0.06
    Activations Density 0.010%

    No Known Activations