© 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. 74889
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and personal reflections on complex topics

    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
     tumble
    -0.06
    lig
    -0.06
    Await
    -0.06
    keterangan
    -0.06
     lak
    -0.06
    SED
    -0.06
     forecasts
    -0.05
     $
    -0.05
    await
    -0.05
    leading
    -0.05
    POSITIVE LOGITS
     guidelines
    0.08
    .scalablytyped
    0.07
     instances
    0.07
     decisions
    0.07
    Ãłng
    0.07
    å¸ĥ
    0.07
     exceptions
    0.07
     decision
    0.07
    abbo
    0.07
    ocaust
    0.07
    Activations Density 0.030%

    No Known Activations