© 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. 129657
    Prev
    Next
    INDEX
    Explanations

    themes of struggle and conflict

    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
    -0.11
    ,
    -0.08
     (
    -0.07
    ;
    -0.07
    Âł
    -0.06
     after
    -0.06
    p
    -0.06
    .
    -0.06
     in
    -0.06
     _
    -0.05
    POSITIVE LOGITS
     nackte
    0.10
    Interop
    0.10
    óng
    0.09
     góc
    0.09
    ystack
    0.08
    ̧
    0.08
    μÏĢο
    0.08
    .Generated
    0.08
    ãģĤãģĴ
    0.08
    TriState
    0.08
    Activations Density 0.009%

    No Known Activations