© 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. 15-LLAMASCOPE-RES-131K
    6. 90176
    Prev
    Next
    INDEX
    Explanations

    instances of a specific condition or recommendation associated with commissions

    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
    odial
    -0.07
    ieder
    -0.07
    latlong
    -0.07
    aiser
    -0.07
    enter
    -0.07
    oda
    -0.06
    è§
    -0.06
    istrov
    -0.06
     Grimm
    -0.06
    inz
    -0.06
    POSITIVE LOGITS
    vat
    0.07
    StreamReader
    0.07
    kov
    0.06
    _Record
    0.06
     Basket
    0.06
    esc
    0.06
    ology
    0.06
     Transparency
    0.06
    voir
    0.06
    nal
    0.06
    Activations Density 0.000%

    No Known Activations