© 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. 97088
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or codes

    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
    oire
    -0.08
    ieten
    -0.07
    adic
    -0.07
    round
    -0.07
    greg
    -0.07
    FX
    -0.06
    acional
    -0.06
    Votes
    -0.06
    iments
    -0.06
    iten
    -0.06
    POSITIVE LOGITS
    èģ
    0.07
    jal
    0.06
    ва
    0.06
    ListNode
    0.06
     FLOAT
    0.06
    POSITORY
    0.06
    ieu
    0.06
     chân
    0.06
    ãĢĤãĢĤ↵↵
    0.06
     ComVisible
    0.06
    Activations Density 0.001%

    No Known Activations