© 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. 17-LLAMASCOPE-RES-131K
    11. 83146
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to programming and system management

    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
     vale
    -0.08
    zcze
    -0.07
    lesh
    -0.07
    dden
    -0.07
    anging
    -0.06
    itou
    -0.06
    ingly
    -0.06
    joy
    -0.06
     baja
    -0.06
    aleb
    -0.06
    POSITIVE LOGITS
    íݸ
    0.07
    APT
    0.07
    ůst
    0.06
    358
    0.06
    WithEmail
    0.06
    kil
    0.06
    اÛĮØ´
    0.06
    δÏħ
    0.06
    arkin
    0.06
     seeded
    0.06
    Activations Density 0.036%

    No Known Activations