© 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. 55130
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating preference or connection

    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
     more
    -0.06
     only
    -0.06
    /
    -0.06
    ,
    -0.06
    oret
    -0.06
    zd
    -0.06
     increasingly
    -0.06
     seamless
    -0.06
    ãģ£ãģ¨
    -0.06
    stra
    -0.06
    POSITIVE LOGITS
    205
    0.08
    PÅĻi
    0.08
    _SAN
    0.08
    ÑıÑĩ
    0.08
    lsru
    0.07
    ewire
    0.07
    ebin
    0.07
    ħn
    0.07
    Když
    0.07
    tsy
    0.07
    Activations Density 0.001%

    No Known Activations