© 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. 80755
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices, particularly smartphones

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    θι
    -0.08
    NECT
    -0.08
    ɵ
    -0.08
    .updateDynamic
    -0.08
    ROKE
    -0.08
    afx
    -0.07
    AILABLE
    -0.07
    COND
    -0.07
     CDDL
    -0.07
    $MESS
    -0.07
    POSITIVE LOGITS
    GC
    0.06
     Me
    0.06
     Du
    0.06
     Dual
    0.06
     Creek
    0.06
     Twin
    0.05
    overs
    0.05
     runtime
    0.05
     s
    0.05
     hybrid
    0.05
    Activations Density 0.014%

    No Known Activations