© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106990
    Prev
    Next
    INDEX
    Explanations

    terms related to production and packaging in a statistical or reporting context

    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
    ÑĢеж
    -0.07
    reff
    -0.07
    618
    -0.07
     Bay
    -0.07
    bay
    -0.06
    IEL
    -0.06
    ninger
    -0.06
    <tag
    -0.06
     bay
    -0.06
    esc
    -0.06
    POSITIVE LOGITS
     Mitar
    0.06
    ibble
    0.06
    NAL
    0.06
     beni
    0.06
     Malone
    0.06
     disclosures
    0.06
    RNA
    0.06
     insider
    0.06
    _gift
    0.06
    èī
    0.06
    Activations Density 0.000%

    No Known Activations