© 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. 86544
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance and referencing protocols

    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
    attro
    -0.07
    ATTLE
    -0.07
    ÑĤÑĮ
    -0.07
    ulti
    -0.07
    annt
    -0.07
    ÄĻd
    -0.07
    ayah
    -0.06
    ición
    -0.06
    epam
    -0.06
    razier
    -0.06
    POSITIVE LOGITS
    angi
    0.08
    zet
    0.07
    ross
    0.07
    /exec
    0.06
     punch
    0.06
    _OPER
    0.06
     gratuits
    0.06
    jh
    0.06
     Myers
    0.06
     Darren
    0.06
    Activations Density 0.005%

    No Known Activations