© 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. 71434
    Prev
    Next
    INDEX
    Explanations

    references to rankings or lists

    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
    wil
    -0.07
    éº
    -0.06
    èħ¹
    -0.06
    istrate
    -0.06
     nghiá»ĩp
    -0.06
    imps
    -0.06
    .Instance
    -0.06
     sph
    -0.06
    aign
    -0.06
    -bin
    -0.06
    POSITIVE LOGITS
     list
    0.10
     ÑģпиÑģка
    0.09
     lists
    0.09
     sublist
    0.08
     seznam
    0.08
     lista
    0.08
    list
    0.08
     List
    0.07
    åĪ·
    0.07
     ÑģпиÑģок
    0.07
    Activations Density 0.019%

    No Known Activations