© 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. 89992
    Prev
    Next
    INDEX
    Explanations

    terms related to food, particularly appetizers and courses

    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
    aba
    -0.07
    usercontent
    -0.07
    _extensions
    -0.07
    assi
    -0.07
    -settings
    -0.07
    åij¨å¹´
    -0.07
    /INFO
    -0.06
    oe
    -0.06
    ftp
    -0.06
    -Origin
    -0.06
    POSITIVE LOGITS
    edo
    0.07
    -sized
    0.07
    urf
    0.07
    mez
    0.07
    langs
    0.07
    /sn
    0.06
    RLF
    0.06
    ~,
    0.06
    룬
    0.06
    OMPI
    0.06
    Activations Density 0.007%

    No Known Activations