© 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. 57393
    Prev
    Next
    INDEX
    Explanations

    references to castles and significant historical architectures

    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
    ouver
    -0.07
    atif
    -0.07
    éné
    -0.07
    hab
    -0.07
    ksam
    -0.07
    xes
    -0.06
    steller
    -0.06
    大åħ¨
    -0.06
     fatal
    -0.06
    üç
    -0.06
    POSITIVE LOGITS
    ewart
    0.08
    ieri
    0.08
    ertime
    0.07
    Ĥæķ°
    0.07
    URRED
    0.07
    ets
    0.07
    cue
    0.07
    atatype
    0.07
    -like
    0.07
    resses
    0.06
    Activations Density 0.015%

    No Known Activations