© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly in the context of politics or public affairs

    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
    erken
    -0.08
    hood
    -0.08
    er
    -0.07
    SCP
    -0.07
    hard
    -0.07
    pp
    -0.07
     intptr
    -0.07
    rought
    -0.07
    PP
    -0.07
    band
    -0.06
    POSITIVE LOGITS
    gomery
    0.12
    agne
    0.09
    aine
    0.09
    serrat
    0.08
    ainer
    0.08
    aneous
    0.08
    aneously
    0.08
    ics
    0.07
    shire
    0.07
    iers
    0.07
    Activations Density 0.025%

    No Known Activations