© 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. 5-LLAMASCOPE-RES-131K
    11. 126614
    Prev
    Next
    INDEX
    Explanations

    references to film companies and filmmaking entities

    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
    cona
    -0.08
    vice
    -0.07
    _COLLECTION
    -0.07
    avras
    -0.07
    ham
    -0.06
    ely
    -0.06
    avax
    -0.06
    beck
    -0.06
    meld
    -0.06
    ampa
    -0.06
    POSITIVE LOGITS
    ää
    0.07
    rin
    0.07
    IJ
    0.06
    trand
    0.06
     scr
    0.06
    gin
    0.06
    trap
    0.06
     phép
    0.06
    FormatException
    0.06
    shape
    0.06
    Activations Density 0.004%

    No Known Activations