© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127132
    Prev
    Next
    INDEX
    Explanations

    various forms and conjugations of the verb "go."

    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
    abr
    -0.07
    assen
    -0.07
    elson
    -0.06
    ajor
    -0.06
    apter
    -0.06
    ulse
    -0.06
    ced
    -0.06
    esk
    -0.06
    ixel
    -0.06
    aje
    -0.06
    POSITIVE LOGITS
    VERN
    0.09
    thic
    0.09
    /fwlink
    0.09
    ÅĽcie
    0.08
    ekli
    0.08
    SSIP
    0.07
    zilla
    0.07
    iaux
    0.07
     extinct
    0.07
    ÅĤÄħ
    0.07
    Activations Density 0.023%

    No Known Activations