© 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. 9-LLAMASCOPE-RES-131K
    11. 98916
    Prev
    Next
    INDEX
    Explanations

    components related to software development tools and frameworks

    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
    vard
    -0.06
    ÅĤu
    -0.06
     hen
    -0.06
    ưỡng
    -0.06
    aversable
    -0.06
     Sheldon
    -0.06
    ToOne
    -0.06
    лаж
    -0.05
     terms
    -0.05
     childhood
    -0.05
    POSITIVE LOGITS
     INTERRUPTION
    0.07
    ics
    0.06
     breat
    0.06
    ÅĻez
    0.06
    ůj
    0.06
    riba
    0.06
    _busy
    0.06
    ÑĨвеÑĤ
    0.06
    Absent
    0.06
    rý
    0.06
    Activations Density 0.007%

    No Known Activations