© 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. 60965
    Prev
    Next
    INDEX
    Explanations

    names, especially surnames and titles related to individuals

    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
    andum
    -0.07
    ERRU
    -0.06
    issan
    -0.06
    ã
    -0.06
     tam
    -0.06
    nis
    -0.06
    -в
    -0.06
    tam
    -0.06
     Robert
    -0.06
    onders
    -0.06
    POSITIVE LOGITS
    _IGNORE
    0.08
    tle
    0.08
    tered
    0.08
    enberg
    0.08
    aversal
    0.07
    skin
    0.07
    eatures
    0.07
    /repos
    0.07
    erman
    0.07
    acter
    0.07
    Activations Density 0.004%

    No Known Activations