© 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. 17-LLAMASCOPE-RES-131K
    11. 82873
    Prev
    Next
    INDEX
    Explanations

    references to internal processes and features in a technical context

    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
    anim
    -0.06
     Kings
    -0.06
     hab
    -0.06
    æ¤ħ
    -0.06
     Hab
    -0.06
    licit
    -0.06
    .DAL
    -0.06
    bor
    -0.06
    unc
    -0.06
    -d
    -0.05
    POSITIVE LOGITS
     INTERNAL
    0.12
     internal
    0.12
    åĨħéĥ¨
    0.10
    internal
    0.10
     Internal
    0.10
    Internal
    0.10
     internals
    0.09
    _internal
    0.09
    (internal
    0.09
    /internal
    0.09
    Activations Density 0.019%

    No Known Activations