© 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. 15-LLAMASCOPE-RES-131K
    11. 61954
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and specific phrases associated with actions

    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
    aurus
    -0.08
     kup
    -0.08
    omanip
    -0.08
    edBy
    -0.08
    pdata
    -0.08
    uur
    -0.07
    vert
    -0.07
    .AI
    -0.07
    iá»ĩp
    -0.07
    edla
    -0.07
    POSITIVE LOGITS
     boot
    0.07
    ion
    0.06
    chan
    0.06
    hetto
    0.06
    yon
    0.06
     Loc
    0.06
    sg
    0.06
     Boot
    0.05
    otte
    0.05
    gu
    0.05
    Activations Density 0.014%

    No Known Activations