© 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. 57561
    Prev
    Next
    INDEX
    Explanations

    specific measurements or quantities associated with products and their environmental impacts

    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
    ueur
    -0.07
    vrd
    -0.06
    ensa
    -0.06
     Ñĩим
    -0.06
    ouch
    -0.06
    istros
    -0.06
    bard
    -0.06
    olah
    -0.06
     subsystem
    -0.06
    .zero
    -0.06
    POSITIVE LOGITS
    缸å½ĵ
    0.08
    bled
    0.07
     typically
    0.07
     equivalent
    0.06
    ormal
    0.06
     Rough
    0.06
    ¶Ī
    0.06
    Equivalent
    0.06
    rough
    0.06
     ||=
    0.06
    Activations Density 0.031%

    No Known Activations