© 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. 86651
    Prev
    Next
    INDEX
    Explanations

    technical terms and procedures related to scientific experiments

    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
    ou
    -0.06
     adv
    -0.06
     negoci
    -0.06
     lubric
    -0.05
     icy
    -0.05
    _filtered
    -0.05
    stal
    -0.05
    奴
    -0.05
    Ñĸв
    -0.05
    chl
    -0.05
    POSITIVE LOGITS
     oven
    0.11
     heat
    0.11
     heating
    0.11
    çĦ¼
    0.10
     bake
    0.10
     Heat
    0.10
     furnace
    0.10
    Heat
    0.09
     temperatures
    0.09
     temperature
    0.09
    Activations Density 0.028%

    No Known Activations