© 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. 86406
    Prev
    Next
    INDEX
    Explanations

    numeric values or dates associated with higher significance or importance

    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
    hte
    -0.08
    æĭħå½ĵ
    -0.07
    ÅĻez
    -0.07
    ometr
    -0.07
    ozo
    -0.07
    StringRef
    -0.07
    .pitch
    -0.07
    걸
    -0.07
    ataire
    -0.07
    تÙī
    -0.07
    POSITIVE LOGITS
    Stuff
    0.06
    clock
    0.06
    468
    0.06
    oretical
    0.06
    oret
    0.06
     clock
    0.06
     tracks
    0.06
    -clock
    0.06
     ins
    0.06
    ns
    0.05
    Activations Density 0.001%

    No Known Activations