© 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. 9-LLAMASCOPE-RES-131K
    11. 95503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating references or acknowledgments

    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
    tam
    -0.07
    urr
    -0.06
    ientos
    -0.06
    reme
    -0.06
    onds
    -0.06
     Hib
    -0.06
     PAC
    -0.06
    acker
    -0.05
    idden
    -0.05
    eness
    -0.05
    POSITIVE LOGITS
    afort
    0.07
     vur
    0.07
    irut
    0.06
     recent
    0.06
    --------------------------------------------------------------------------↵
    0.06
    ì§ĢìĽIJ
    0.06
     ISO
    0.06
     ÑĢÑĸв
    0.06
    ikel
    0.06
    stime
    0.06
    Activations Density 0.014%

    No Known Activations