© 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. 28763
    Prev
    Next
    INDEX
    Explanations

    concepts related to preparation and effort in achieving goals

    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
    Äįe
    -0.07
    asca
    -0.07
    agas
    -0.07
    villa
    -0.07
    ozo
    -0.06
    ο
    -0.06
    unca
    -0.06
     imp
    -0.06
    cie
    -0.06
    razier
    -0.06
    POSITIVE LOGITS
    æīįèĥ½
    0.10
     Yours
    0.06
    ToWorld
    0.06
    erties
    0.06
    InMillis
    0.06
    OLD
    0.06
    udios
    0.06
    ToFront
    0.06
    ortex
    0.06
    LOTS
    0.06
    Activations Density 0.025%

    No Known Activations