© 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. 130884
    Prev
    Next
    INDEX
    Explanations

    phrases indicating detailed descriptions or specifications

    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
    elli
    -0.06
    اÙĦص
    -0.06
    863
    -0.06
    заб
    -0.06
    illis
    -0.06
     Wein
    -0.06
    zsche
    -0.06
    issance
    -0.06
    693
    -0.06
    หย
    -0.05
    POSITIVE LOGITS
    BaseContext
    0.07
    osyal
    0.07
    geois
    0.07
    ((__
    0.07
    ATAL
    0.07
     ESP
    0.06
    otel
    0.06
    μοί
    0.06
    å½
    0.06
    Denied
    0.06
    Activations Density 0.000%

    No Known Activations