© 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. 9-LLAMASCOPE-RES-131K
    11. 97224
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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
     reason
    -0.07
    isc
    -0.07
    ,
    -0.07
    per
    -0.06
    zone
    -0.06
    lest
    -0.06
    gov
    -0.06
    -
    -0.06
    itional
    -0.06
     prote
    -0.06
    POSITIVE LOGITS
    ież
    0.08
    ÑģоÑĤ
    0.08
    ÄįÃŃ
    0.08
    mPid
    0.08
    리그
    0.07
    unce
    0.07
    TriState
    0.07
     졸
    0.07
    (TIM
    0.07
    -LAST
    0.07
    Activations Density 0.035%

    No Known Activations