© 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. 75883
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating inclusivity or plurality

    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
    ÑĪÑĮ
    -0.07
    ÙĪÙĨا
    -0.07
    chio
    -0.07
    enze
    -0.07
    ÑĤÑİ
    -0.07
    åIJ¾
    -0.06
    /cms
    -0.06
    liš
    -0.06
    ì§ij
    -0.06
    aru
    -0.06
    POSITIVE LOGITS
     any
    0.07
     kind
    0.07
    /or
    0.07
    igm
    0.07
    /all
    0.07
    rogen
    0.06
    aan
    0.06
     sized
    0.06
    lene
    0.06
     forthcoming
    0.06
    Activations Density 0.003%

    No Known Activations