© 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. 83117
    Prev
    Next
    INDEX
    Explanations

    inquiries about programming and technical solutions

    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
     деÑĢ
    -0.07
    udget
    -0.06
    òi
    -0.06
    ิà¹ī
    -0.06
    borg
    -0.06
    riangle
    -0.06
     Cave
    -0.06
    /releases
    -0.06
    _Cmd
    -0.06
    olumn
    -0.06
    POSITIVE LOGITS
    lob
    0.08
    atile
    0.07
     please
    0.06
    รม
    0.06
    hung
    0.06
    gger
    0.06
     Gn
    0.06
    doch
    0.06
     labs
    0.06
    rap
    0.06
    Activations Density 0.046%

    No Known Activations