© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to changing or modifying various elements

    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
    immel
    -0.07
    GIS
    -0.06
    bour
    -0.06
    berman
    -0.06
    heit
    -0.06
    brush
    -0.06
    ometric
    -0.06
    atis
    -0.05
    üt
    -0.05
    аÑĢÑħ
    -0.05
    POSITIVE LOGITS
     Seasons
    0.07
    wap
    0.06
    jon
    0.06
     Conte
    0.06
     Gür
    0.06
    aggi
    0.06
    492
    0.06
    asley
    0.06
     snap
    0.06
    417
    0.06
    Activations Density 0.000%

    No Known Activations