© 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. 86535
    Prev
    Next
    INDEX
    Explanations

    references to structured lists or enumeration

    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
    steen
    -0.07
    rop
    -0.06
    oor
    -0.06
    ’n
    -0.06
    SM
    -0.06
    ”
    -0.06
     etc
    -0.06
    rib
    -0.06
    ROP
    -0.06
    zin
    -0.05
    POSITIVE LOGITS
    InstanceOf
    0.07
    /OR
    0.07
     "".
    0.07
    åħĭæĸ¯
    0.07
    ksi
    0.07
    wnd
    0.07
    волÑı
    0.06
     ------------------------------------------------------------
    0.06
    ë§ī
    0.06
    î
    0.06
    Activations Density 0.017%

    No Known Activations