© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42526
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refer" and its variants

    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
    spacer
    -0.08
    ery
    -0.08
    elier
    -0.08
    inz
    -0.07
    ury
    -0.07
    eful
    -0.06
    osing
    -0.06
    _pf
    -0.06
    ulu
    -0.06
    Accessor
    -0.06
    POSITIVE LOGITS
    ential
    0.09
    entially
    0.09
    encing
    0.08
    refer
    0.08
     refer
    0.08
     Refer
    0.08
    Refer
    0.08
    erence
    0.07
    .Reference
    0.07
     kepada
    0.07
    Activations Density 0.014%

    No Known Activations