© 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. 94232
    Prev
    Next
    INDEX
    Explanations

    contextually significant identifiers or references related to data or topics

    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
    rane
    -0.08
    itore
    -0.07
    omen
    -0.07
    gate
    -0.06
    ยม
    -0.06
    #
    -0.06
    éľŀ
    -0.06
    emmel
    -0.06
     indiv
    -0.06
    ield
    -0.06
    POSITIVE LOGITS
    ingo
    0.08
    inski
    0.07
    ç¾Ĭ
    0.06
    ãĢħ
    0.06
     Abel
    0.06
    sı
    0.06
    anks
    0.06
    æijĩ
    0.06
    еÑģÑĤв
    0.06
    aul
    0.06
    Activations Density 0.001%

    No Known Activations