© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87626
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    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
    htag
    -0.09
    rcode
    -0.07
    .internet
    -0.07
    елиÑĩ
    -0.07
     Pes
    -0.07
    (...)↵
    -0.07
    Pes
    -0.07
    åŃĶ
    -0.07
    ãĥĨãĥ«
    -0.07
    алÑĸ
    -0.06
    POSITIVE LOGITS
    ë¡Ģ
    0.07
    ynet
    0.07
    _EXPORT
    0.06
     bet
    0.06
    igm
    0.06
    erk
    0.06
    ikan
    0.06
    eric
    0.06
     Bet
    0.05
    edl
    0.05
    Activations Density 0.000%

    No Known Activations