© 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. 56413
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to programming and system operations

    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
    iloc
    -0.07
    esson
    -0.07
    ilet
    -0.06
    emoc
    -0.06
     Reich
    -0.06
     Gest
    -0.06
    AFX
    -0.06
    ltk
    -0.06
    ree
    -0.06
    zs
    -0.06
    POSITIVE LOGITS
     chan
    0.07
    çİ
    0.07
    говоÑĢ
    0.06
    infeld
    0.06
    hazi
    0.06
     %+
    0.06
    idelberg
    0.06
    orr
    0.06
     gratuites
    0.06
    stå
    0.06
    Activations Density 0.149%

    No Known Activations