© 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. 29478
    Prev
    Next
    INDEX
    Explanations

    references to website users and ownership

    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
    ough
    -0.06
    .met
    -0.06
    ÑĥÑĤи
    -0.06
    eya
    -0.06
     overhead
    -0.06
     overl
    -0.06
    erce
    -0.06
    able
    -0.06
    ered
    -0.05
     ISBN
    -0.05
    POSITIVE LOGITS
     individual
    0.07
    ullan
    0.07
    individual
    0.07
    lav
    0.07
    é¼
    0.07
    ivals
    0.07
    rello
    0.06
    .scalablytyped
    0.06
    anggan
    0.06
    visitor
    0.06
    Activations Density 0.004%

    No Known Activations