© 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. 125892
    Prev
    Next
    INDEX
    Explanations

    elements related to design and architectural considerations

    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
    raci
    -0.08
    uales
    -0.08
    称
    -0.07
    åĦĢ
    -0.07
    -overlay
    -0.07
     tomorrow
    -0.07
    lassian
    -0.07
    erton
    -0.07
    prs
    -0.07
    igits
    -0.06
    POSITIVE LOGITS
     design
    0.09
     Design
    0.08
    Design
    0.08
     challenge
    0.08
    .constraints
    0.07
     initially
    0.07
    -design
    0.07
     originally
    0.07
     outset
    0.07
    .Constraint
    0.07
    Activations Density 0.050%

    No Known Activations