© 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. 76843
    Prev
    Next
    INDEX
    Explanations

    references to live television or performance events

    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
    _mE
    -0.07
    _mD
    -0.07
    _tD
    -0.07
    _mB
    -0.07
    cube
    -0.07
    auga
    -0.06
    aget
    -0.06
    "class
    -0.06
    _mC
    -0.06
    _tF
    -0.06
    POSITIVE LOGITS
    isode
    0.07
    ãĥ©ãĥ¼
    0.06
    ige
    0.06
    lush
    0.06
    acia
    0.06
     telesc
    0.06
    abcdefghijkl
    0.06
    ture
    0.06
     Edison
    0.06
    _ESCAPE
    0.06
    Activations Density 0.000%

    No Known Activations