© 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. 17-LLAMASCOPE-RES-131K
    11. 125676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypotheses or explanations for observed phenomena

    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
    ombok
    -0.06
    Ī¬
    -0.06
    aos
    -0.06
    etu
    -0.06
    adel
    -0.06
    loy
    -0.06
    hod
    -0.06
    olumn
    -0.06
    riott
    -0.06
    jected
    -0.06
    POSITIVE LOGITS
     due
    0.09
     caused
    0.08
     result
    0.08
     simply
    0.07
    due
    0.07
     بسبب
    0.07
    .scalablytyped
    0.07
     because
    0.07
     CAUSED
    0.07
    uhl
    0.07
    Activations Density 0.036%

    No Known Activations