© 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. 3251
    Prev
    Next
    INDEX
    Explanations

    user inquiries and contact information

    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
    ät
    -0.06
    forward
    -0.06
     Abs
    -0.06
    498
    -0.06
    abs
    -0.06
     interv
    -0.06
     searches
    -0.06
    flower
    -0.06
     Asked
    -0.05
    rawn
    -0.05
    POSITIVE LOGITS
    ulia
    0.08
     submission
    0.08
     editors
    0.08
    usat
    0.08
    Editors
    0.07
    Submission
    0.07
    -editor
    0.07
     Submit
    0.07
    Pitch
    0.07
     Submission
    0.07
    Activations Density 0.010%

    No Known Activations