© 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. 744
    Prev
    Next
    INDEX
    Explanations

    numerical references or counts related to participation or entry requirements

    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
    chner
    -0.07
    reau
    -0.06
     Nob
    -0.06
     Carrier
    -0.06
     Hayes
    -0.06
    otte
    -0.06
     Gene
    -0.06
    pic
    -0.06
    æĭ¥
    -0.06
     comp
    -0.06
    POSITIVE LOGITS
    @nate
    0.07
    oop
    0.07
    ÑĢей
    0.07
    лаÑĩ
    0.06
    lass
    0.06
    FORE
    0.06
    andes
    0.06
    lamp
    0.06
    sexual
    0.06
    ÑĤак
    0.06
    Activations Density 0.002%

    No Known Activations