© 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. 71599
    Prev
    Next
    INDEX
    Explanations

    the word "all."

    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
     count
    -0.07
     barg
    -0.06
     relative
    -0.06
    _front
    -0.06
    indsight
    -0.05
    chg
    -0.05
     nearly
    -0.05
     smoothed
    -0.05
     bound
    -0.05
     tÃŃm
    -0.05
    POSITIVE LOGITS
    iesz
    0.07
    OffsetTable
    0.07
    RowAt
    0.07
    ÅŁk
    0.07
    fel
    0.07
     ì°
    0.07
    è²»
    0.07
    elier
    0.07
    اض
    0.07
    .bio
    0.07
    Activations Density 0.000%

    No Known Activations