© 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. 9-LLAMASCOPE-RES-131K
    11. 97960
    Prev
    Next
    INDEX
    Explanations

    instances of multifaceted or complex concepts

    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
    alta
    -0.07
    itzer
    -0.07
    аÑĤок
    -0.07
    _VAR
    -0.06
    опÑĢоÑģ
    -0.06
    QUEST
    -0.06
    _ACC
    -0.06
    .cost
    -0.06
     vieille
    -0.06
     иÑģÑĩ
    -0.06
    POSITIVE LOGITS
    630
    0.06
    apos
    0.06
    ocab
    0.06
    agne
    0.06
    elib
    0.06
    635
    0.06
    ety
    0.06
    anager
    0.06
    665
    0.06
    nbsp
    0.06
    Activations Density 0.393%

    No Known Activations