© 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. 17-LLAMASCOPE-RES-131K
    11. 42067
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relationships between clauses or actions

    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
    619
    -0.07
    antine
    -0.07
    ChangedEventArgs
    -0.07
    .scalablytyped
    -0.06
    íĨłíĨł
    -0.06
    ì£
    -0.06
    abe
    -0.06
    Vtbl
    -0.06
    ê±°ëŀĺê°Ģ
    -0.06
     обÑģÑĤ
    -0.06
    POSITIVE LOGITS
     return
    0.08
    onym
    0.07
    rium
    0.07
    athing
    0.07
    eph
    0.07
     optionally
    0.07
     Genius
    0.07
     update
    0.06
    return
    0.06
    orta
    0.06
    Activations Density 0.032%

    No Known Activations