© 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. 9-LLAMASCOPE-RES-131K
    11. 96638
    Prev
    Next
    INDEX
    Explanations

    terms relating to legitimacy and interests

    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
    deaux
    -0.08
    ofday
    -0.08
    HAND
    -0.07
     prefs
    -0.07
    ILT
    -0.07
    ÅĻev
    -0.07
     видÑĥ
    -0.07
     astore
    -0.07
    .mods
    -0.07
    hana
    -0.07
    POSITIVE LOGITS
    529
    0.06
    edom
    0.06
    518
    0.05
     nominee
    0.05
    ódigo
    0.05
    ासन
    0.05
    achen
    0.05
     David
    0.05
    "
    0.05
     global
    0.05
    Activations Density 0.000%

    No Known Activations