© 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 EvalsExportsinterp-engineNEWAPI 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. 27520
    Prev
    Next
    INDEX
    Explanations

    HTML heading tags

    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
     latter
    -0.07
    _iff
    -0.07
    ihn
    -0.06
    دÙĬØ«
    -0.06
     Slut
    -0.06
    ppo
    -0.06
    -trade
    -0.06
    caster
    -0.06
    485
    -0.06
    ificio
    -0.06
    POSITIVE LOGITS
    pare
    0.08
    ouis
    0.07
    esper
    0.07
     Bölüm
    0.06
     McKay
    0.06
    cka
    0.06
    tails
    0.06
    ¼
    0.06
    jerne
    0.06
     Mec
    0.06
    Activations Density 0.005%

    No Known Activations