© 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. 93620
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to cases in scientific contexts

    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
    ocity
    -0.08
    (MPI
    -0.07
    GuidId
    -0.07
     Kemp
    -0.06
    bens
    -0.06
     riders
    -0.06
    rido
    -0.06
    è°ĵ
    -0.06
    udd
    -0.06
     recru
    -0.06
    POSITIVE LOGITS
     Amateur
    0.10
     Ham
    0.08
     ham
    0.08
    .ham
    0.08
     amateur
    0.08
    thon
    0.07
    Ham
    0.07
    rane
    0.07
    anten
    0.07
     station
    0.07
    Activations Density 0.006%

    No Known Activations