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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118475
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific attributes related to measurements and dimensions

    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
    yre
    -0.07
    ä½ĵ
    -0.06
    preneur
    -0.06
    ellar
    -0.06
    é«Ķ
    -0.06
    apel
    -0.06
    ContextHolder
    -0.06
    @mail
    -0.06
    enty
    -0.06
    ness
    -0.05
    POSITIVE LOGITS
    kest
    0.07
     tuz
    0.07
    boru
    0.07
     '&'
    0.07
    stoupil
    0.06
     neust
    0.06
    tracks
    0.06
    CRY
    0.06
    大åħ¨
    0.06
    #
    0.06
    Activations Density 0.000%

    No Known Activations