© 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. 61219
    Prev
    Next
    INDEX
    Explanations

    references to ranking and lists of notable entities or characteristics

    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
    AdapterFactory
    -0.07
     many
    -0.07
    ëĭ´
    -0.07
    ŀ
    -0.07
     such
    -0.06
    oller
    -0.06
    ختÙĩ
    -0.06
     itself
    -0.06
    žel
    -0.06
     Twice
    -0.06
    POSITIVE LOGITS
    ined
    0.07
    nia
    0.07
    ½
    0.07
    /show
    0.06
    akhir
    0.06
    inois
    0.06
    ines
    0.06
    alim
    0.06
     Lambert
    0.06
    apesh
    0.06
    Activations Density 0.018%

    No Known Activations