© 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. 15-LLAMASCOPE-RES-131K
    11. 26946
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and scheduling related terms

    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
    /stdc
    -0.07
    283
    -0.07
    hta
    -0.07
     gag
    -0.06
    ute
    -0.06
    amic
    -0.06
    аÑĤег
    -0.06
    zew
    -0.06
    onaut
    -0.06
    CO
    -0.06
    POSITIVE LOGITS
    enant
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
    ourke
    0.06
    éijij
    0.06
     CDDL
    0.06
    Ctrls
    0.06
    oader
    0.06
    ìļĶìĿ¼
    0.06
     à¤Ńर
    0.06
    oub
    0.06
    Activations Density 0.005%

    No Known Activations