© 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. 106738
    Prev
    Next
    INDEX
    Explanations

    elements related to database management and data communication

    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
    Ưá»
    -0.08
    kili
    -0.07
    esini
    -0.07
    pectral
    -0.07
    onical
    -0.07
    rades
    -0.07
    erval
    -0.06
    nic
    -0.06
    .ribbon
    -0.06
    rego
    -0.06
    POSITIVE LOGITS
    iene
    0.07
    pure
    0.07
     Pure
    0.06
     pure
    0.06
    483
    0.06
    ception
    0.06
    Pure
    0.06
     Lowest
    0.06
    ĸī
    0.06
     Muscle
    0.05
    Activations Density 0.003%

    No Known Activations