© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88491
    Prev
    Next
    INDEX
    Explanations

    the mention of player names, particularly those with the substring "rell"

    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
    ed
    -0.12
    ا
    -0.08
    eward
    -0.07
    edic
    -0.07
    die
    -0.07
    enberg
    -0.07
    elim
    -0.07
    êµ´
    -0.07
    edis
    -0.07
    dens
    -0.07
    POSITIVE LOGITS
    uxe
    0.08
    ino
    0.07
    tract
    0.07
    lectual
    0.07
    stown
    0.07
    adora
    0.06
    agos
    0.06
    igaret
    0.06
    led
    0.06
    itos
    0.06
    Activations Density 0.020%

    No Known Activations