© 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 EvalsExportsinterp-engineNEWAPI 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. 107564
    Prev
    Next
    INDEX
    Explanations

    contextual phrases indicating causation or complex relationships

    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
    kazy
    -0.07
    илÑı
    -0.07
    iya
    -0.06
    kola
    -0.06
    fillType
    -0.06
     düzenlenen
    -0.06
     Counts
    -0.06
    igel
    -0.06
    éo
    -0.06
    anke
    -0.06
    POSITIVE LOGITS
    ADB
    0.07
     might
    0.06
    ahlen
    0.06
    ikler
    0.06
    upon
    0.06
     together
    0.06
     incident
    0.06
     enc
    0.06
     would
    0.06
     Speaker
    0.06
    Activations Density 0.023%

    No Known Activations