© 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. 9-LLAMASCOPE-RES-131K
    11. 97853
    Prev
    Next
    INDEX
    Explanations

    specific names or titles, particularly in academic or bureaucratic contexts

    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
    ptype
    -0.07
    ambre
    -0.07
    otron
    -0.07
    íĥĢìĿ´
    -0.07
     tolua
    -0.07
    ék
    -0.07
    ัม
    -0.06
    ahlen
    -0.06
    аÑĢÑĮ
    -0.06
    opping
    -0.06
    POSITIVE LOGITS
     Blackburn
    0.06
     Abed
    0.06
    ÑģÑĤво
    0.06
    Ľi
    0.06
     èī
    0.05
    İ
    0.05
     colomb
    0.05
    åIJ¯
    0.05
    alm
    0.05
    alf
    0.05
    Activations Density 0.120%

    No Known Activations