© 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. 126240
    Prev
    Next
    INDEX
    Explanations

    numerical references and specific years related to film history

    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
    sez
    -0.08
    -Ñħ
    -0.07
    eration
    -0.07
    /feed
    -0.07
    ippers
    -0.07
    afs
    -0.07
    stoff
    -0.07
    ıf
    -0.07
    /Gate
    -0.06
    ıt
    -0.06
    POSITIVE LOGITS
    çĽijåIJ¬é¡µéĿ¢
    0.07
    786
    0.06
    iek
    0.06
    HEME
    0.06
    pling
    0.06
    700
    0.06
    atsapp
    0.06
    andler
    0.06
    aidu
    0.06
     NSStringFromClass
    0.06
    Activations Density 0.008%

    No Known Activations