© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29635
    Prev
    Next
    INDEX
    Explanations

    references to measurements and their related contexts

    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
    егоÑĢ
    -0.08
    essler
    -0.07
    ứng
    -0.07
    Ñĸг
    -0.07
    icari
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    ãģĹãģ¦ãĤĭ
    -0.07
    ắn
    -0.07
    /frame
    -0.07
     ?><?
    -0.07
    POSITIVE LOGITS
    @student
    0.06
    483
    0.05
    ups
    0.05
    evenodd
    0.05
    ffffffff
    0.05
    ulado
    0.05
     Both
    0.05
    403
    0.05
    filer
    0.05
    O
    0.05
    Activations Density 0.000%

    No Known Activations