© 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. 93553
    Prev
    Next
    INDEX
    Explanations

    references to archival records and scrapbooks

    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
    xn
    -0.07
    ething
    -0.07
    ána
    -0.07
    antha
    -0.06
    sson
    -0.06
    anth
    -0.06
    shared
    -0.06
    vik
    -0.06
    è³ŀ
    -0.06
    ocy
    -0.06
    POSITIVE LOGITS
     collection
    0.07
    BCM
    0.06
    ayar
    0.06
    SCII
    0.06
    _Framework
    0.06
     Photograph
    0.06
    actionDate
    0.06
    legen
    0.06
     ragaz
    0.06
    кол
    0.06
    Activations Density 0.003%

    No Known Activations