© 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. 78543
    Prev
    Next
    INDEX
    Explanations

    requests for inclusion or specification of information in documents

    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
    eping
    -0.06
     Ins
    -0.06
    ira
    -0.06
    erring
    -0.06
    éĩį大
    -0.06
     mere
    -0.06
    aki
    -0.06
     Shapiro
    -0.06
    gn
    -0.05
     Cunningham
    -0.05
    POSITIVE LOGITS
    ystate
    0.07
    endum
    0.07
    ëĿ½
    0.07
    psc
    0.07
    kea
    0.07
    _fwd
    0.07
    extra
    0.07
    वत
    0.07
    ITHER
    0.07
    ãĥ¯ãĥ¼
    0.07
    Activations Density 0.015%

    No Known Activations