© 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. 15-LLAMASCOPE-RES-131K
    11. 90284
    Prev
    Next
    INDEX
    Explanations

    clauses and phrases that specify details or conditions

    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
    ÑĢÑĥб
    -0.07
    ViewState
    -0.07
    .Marshal
    -0.07
    سÙĬÙĨ
    -0.07
    à¹īาหà¸Ļ
    -0.07
    iler
    -0.07
    /DD
    -0.07
    νά
    -0.07
    antlr
    -0.06
    égor
    -0.06
    POSITIVE LOGITS
    opsy
    0.07
    coat
    0.07
    ers
    0.07
    elt
    0.06
     leads
    0.06
    arp
    0.06
     basically
    0.06
     fer
    0.06
    which
    0.06
     merupakan
    0.05
    Activations Density 0.043%

    No Known Activations