© 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. 15-LLAMASCOPE-RES-131K
    11. 88705
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proposals or changes related to crime and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology within programming documentation, mathematical expressions, and technical writing, often referring to parameters, variables, or operations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    -list
    -0.06
     Oval
    -0.06
     Pazar
    -0.05
    ãĥ¼ãĥĪ
    -0.05
    wine
    -0.05
     Intelligent
    -0.05
    oyal
    -0.05
     Throne
    -0.05
    ,
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    XMLElement
    0.08
    sdale
    0.08
    ufac
    0.08
    lagen
    0.07
     McCartney
    0.07
    assin
    0.07
    allon
    0.07
    ADDE
    0.07
    legg
    0.07
    jev
    0.07
    Activations Density 0.068%

    No Known Activations