© 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. 120694
    Prev
    Next
    INDEX
    Explanations

    components and properties related to mathematical graphs and sets

    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
    oni
    -0.07
     Tick
    -0.07
     tick
    -0.07
    ceph
    -0.07
     Broad
    -0.07
    _SI
    -0.07
    ÂŃi
    -0.06
    Broad
    -0.06
    .flags
    -0.06
     Dou
    -0.06
    POSITIVE LOGITS
     restriction
    0.10
    restricted
    0.09
     restricted
    0.09
    restriction
    0.09
     locally
    0.09
    _restrict
    0.08
     restrictions
    0.08
    Restricted
    0.08
    å±Ģ
    0.07
     restrict
    0.07
    Activations Density 0.264%

    No Known Activations