© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119286
    Prev
    Next
    INDEX
    Explanations

    references to scientific researchers and their contributions

    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
    itis
    -0.07
    atee
    -0.06
    counter
    -0.06
    OUNTER
    -0.06
    fat
    -0.06
    ot
    -0.06
    CHO
    -0.06
     posts
    -0.06
    ounter
    -0.06
    val
    -0.06
    POSITIVE LOGITS
     lead
    0.14
    lead
    0.11
     Lead
    0.10
    Lead
    0.10
     co
    0.10
    _lead
    0.09
     authors
    0.08
    rray
    0.08
    ahren
    0.08
    olley
    0.08
    Activations Density 0.010%

    No Known Activations