© 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. 15-LLAMASCOPE-RES-131K
    11. 752
    Prev
    Next
    INDEX
    Explanations

    numerical data and related symbols

    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
    имÑĥ
    -0.08
    ’Ñı
    -0.08
    ấm
    -0.07
    нима
    -0.07
    оваÑĢи
    -0.07
     बय
    -0.07
    زÙħ
    -0.07
    .getById
    -0.07
    .Keyboard
    -0.07
    _COMPILER
    -0.07
    POSITIVE LOGITS
    #
    0.07
    pter
    0.06
    odo
    0.06
    lacak
    0.06
    _exempt
    0.06
     NavParams
    0.06
    gte
    0.06
     Clan
    0.06
    sis
    0.06
    iale
    0.05
    Activations Density 0.011%

    No Known Activations