© 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. 69997
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or progression

    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
    /from
    -0.09
    /on
    -0.07
    éĢĶ
    -0.06
    adolu
    -0.06
    /about
    -0.06
     Schmidt
    -0.06
    adam
    -0.06
    /how
    -0.06
    éĢŁ
    -0.06
    /out
    -0.06
    POSITIVE LOGITS
     up
    0.11
     out
    0.10
    -up
    0.10
     off
    0.09
    -out
    0.08
    æİī
    0.08
     down
    0.07
     forth
    0.07
     away
    0.07
    -off
    0.07
    Activations Density 0.066%

    No Known Activations