© 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. 15-LLAMASCOPE-RES-131K
    11. 86895
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other connecting words that indicate relationships or continuations in thought

    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
    ksen
    -0.08
    ORIZED
    -0.07
     èī¯
    -0.07
    oux
    -0.07
    uetype
    -0.07
     OVERRIDE
    -0.07
    EFAULT
    -0.07
     mastur
    -0.07
    loh
    -0.07
    IBUTES
    -0.07
    POSITIVE LOGITS
     hi
    0.07
     Hi
    0.06
    843
    0.06
     elkaar
    0.06
     Sala
    0.06
    asser
    0.06
     Slam
    0.06
    uple
    0.06
     domestic
    0.06
    Hi
    0.06
    Activations Density 0.025%

    No Known Activations