© 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. 126172
    Prev
    Next
    INDEX
    Explanations

    guiding principles for personal presentation and behavior in social contexts

    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
    @nate
    -0.06
    uffy
    -0.06
    COMPARE
    -0.06
    auer
    -0.06
    eward
    -0.06
    .acquire
    -0.06
    .obtain
    -0.06
    tej
    -0.06
    enes
    -0.06
    onder
    -0.06
    POSITIVE LOGITS
     don
    0.08
     limit
    0.08
    EDA
    0.07
    don
    0.07
     embrace
    0.07
     pay
    0.07
    Don
    0.06
    avel
    0.06
     СÑĤа
    0.06
    ila
    0.06
    Activations Density 0.019%

    No Known Activations