© 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. 107111
    Prev
    Next
    INDEX
    Explanations

    references to group behavior and collective human experiences

    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
     sometimes
    -0.13
    sometimes
    -0.10
     Sometimes
    -0.10
     might
    -0.09
     maybe
    -0.09
     may
    -0.08
    Sometimes
    -0.08
     possibly
    -0.08
    might
    -0.07
     alone
    -0.07
    POSITIVE LOGITS
    except
    0.08
    Except
    0.08
     except
    0.08
    è¿ĺæĺ¯
    0.08
     Except
    0.07
     either
    0.07
    Å¡ek
    0.07
     Either
    0.07
     EITHER
    0.07
     à¤Ľ
    0.07
    Activations Density 0.071%

    No Known Activations