© 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. 39739
    Prev
    Next
    INDEX
    Explanations

    references to engagement or directives aimed at the reader

    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
    itone
    -0.07
    ocate
    -0.06
    aceous
    -0.06
    ÏĦÎŃ
    -0.06
    atos
    -0.06
    itos
    -0.06
    Ñĥнк
    -0.06
    æĭŁ
    -0.06
    yl
    -0.06
    ometric
    -0.06
    POSITIVE LOGITS
    antu
    0.07
    ADOR
    0.06
    pret
    0.06
     simply
    0.06
    ĸī
    0.06
     see
    0.06
     Tube
    0.06
    ador
    0.06
     Covenant
    0.06
    may
    0.06
    Activations Density 0.025%

    No Known Activations