© 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. 5-LLAMASCOPE-RES-131K
    11. 126024
    Prev
    Next
    INDEX
    Explanations

    technical processes, specifications, or components related to software and programming

    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
    izza
    -0.07
    ëŁī
    -0.06
    æk
    -0.06
    è¡Ĺ
    -0.06
    æ¡Ĥ
    -0.06
    hari
    -0.06
     IPs
    -0.06
    γÏĩ
    -0.06
    chet
    -0.06
     $('[
    -0.06
    POSITIVE LOGITS
    rical
    0.06
    ike
    0.06
    rik
    0.06
    ord
    0.06
    cks
    0.06
    prs
    0.06
    684
    0.06
    ui
    0.06
    yk
    0.06
    PlainText
    0.06
    Activations Density 0.053%

    No Known Activations