© 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. 56022
    Prev
    Next
    INDEX
    Explanations

    concepts related to learning, social interaction, and recognition of individuals or communities

    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
    loat
    -0.07
    dum
    -0.07
    uz
    -0.07
    oom
    -0.06
    ita
    -0.06
    agt
    -0.06
    oodle
    -0.06
     olmayan
    -0.06
    emo
    -0.06
    odu
    -0.06
    POSITIVE LOGITS
     meiden
    0.07
    .IContainer
    0.06
    463
    0.06
    ÐĴС
    0.06
    .mag
    0.06
     türlü
    0.06
    Ưá»
    0.06
    323
    0.06
    isin
    0.06
    /sp
    0.06
    Activations Density 0.044%

    No Known Activations