© 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. 126276
    Prev
    Next
    INDEX
    Explanations

    references to document revisions and identifiers

    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
    emy
    -0.08
    vida
    -0.08
    oya
    -0.07
    ynos
    -0.07
    amic
    -0.07
     EXIT
    -0.07
    ivent
    -0.07
    .gradient
    -0.07
    azine
    -0.07
    पन
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ĭ
    0.06
     ladder
    0.06
    neck
    0.06
     pairing
    0.06
    isser
    0.06
     pair
    0.05
    èªī
    0.05
    alyzer
    0.05
    ãģĤãģĴ
    0.05
    Activations Density 0.001%

    No Known Activations