© 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. 117300
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and their forms

    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
    621
    -0.07
    tog
    -0.07
    æĢ
    -0.06
    åĩ
    -0.06
    iid
    -0.06
    ubar
    -0.06
    çĹ
    -0.06
    wer
    -0.06
    IDL
    -0.06
    }elseif
    -0.06
    POSITIVE LOGITS
     بس
    0.07
    _pull
    0.06
    ço
    0.06
    codegen
    0.06
    atin
    0.06
    nel
    0.06
    Mvc
    0.06
    ãģĹãĤĥ
    0.06
    ATED
    0.06
    getRepository
    0.05
    Activations Density 0.047%

    No Known Activations