© 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 EvalsExportsAPI 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. 58625
    Prev
    Next
    INDEX
    Explanations

    phrases that include "that being said" or similar transitions indicating a change in thought or conclusion

    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
    .Lookup
    -0.07
    amp
    -0.06
    _PROP
    -0.06
    ede
    -0.06
    TEGER
    -0.06
    acho
    -0.06
    inka
    -0.06
    _PO
    -0.06
    INLINE
    -0.06
    rir
    -0.06
    POSITIVE LOGITS
     said
    0.24
    said
    0.19
     say
    0.19
     Said
    0.17
     saying
    0.16
    说
    0.16
    say
    0.15
     Say
    0.14
     says
    0.14
    Say
    0.14
    Activations Density 0.060%

    No Known Activations