© 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 EvalsExportsinterp-engineNEWAPI 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. 104655
    Prev
    Next
    INDEX
    Explanations

    elements related to interactive discussion formats

    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
    éĿ©
    -0.07
    /DTD
    -0.07
    xit
    -0.07
     Conte
    -0.07
    asher
    -0.07
    conte
    -0.06
    insn
    -0.06
    moire
    -0.06
    adro
    -0.06
    .communic
    -0.06
    POSITIVE LOGITS
     questions
    0.12
     Q
    0.12
     Questions
    0.10
     question
    0.09
     audience
    0.09
    questions
    0.09
     Audience
    0.08
     Question
    0.08
    Q
    0.08
     interaction
    0.07
    Activations Density 0.077%

    No Known Activations