© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 127409
    Prev
    Next
    INDEX
    Explanations

    lists or mentions of names associated with specific events or awards

    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
    éal
    -0.07
    aln
    -0.07
    ighest
    -0.07
    ordo
    -0.07
    mma
    -0.07
    gue
    -0.06
    emme
    -0.06
    maal
    -0.06
    evt
    -0.06
    _initializer
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ì§Ģëħ¸
    0.07
    بÙĪاسطة
    0.07
    SenderId
    0.06
    697
    0.06
    ODULE
    0.06
    akis
    0.06
    åľ¨çº¿è§Ĩé¢ij
    0.06
    DeltaTime
    0.06
    jedn
    0.06
    Activations Density 0.008%

    No Known Activations