© 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. 4286
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to geographical locations

    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
    oir
    -0.07
    ovit
    -0.07
    nier
    -0.06
    odie
    -0.06
    indo
    -0.06
    sembl
    -0.06
    ce
    -0.06
    ode
    -0.06
    cea
    -0.06
    riers
    -0.06
    POSITIVE LOGITS
    amp
    0.09
    kili
    0.09
    raquo
    0.09
    rosso
    0.07
     Sür
    0.07
     env
    0.07
     surrounds
    0.06
    amping
    0.06
    _Construct
    0.06
     elsewhere
    0.06
    Activations Density 0.026%

    No Known Activations