© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74732
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically parentheses and commas

    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
    strup
    -0.07
    arrant
    -0.06
     Carlton
    -0.06
    /commons
    -0.06
    IVAL
    -0.06
    891
    -0.06
    eldon
    -0.06
    èĬĿ
    -0.06
    lew
    -0.06
    erece
    -0.06
    POSITIVE LOGITS
     ...(
    0.07
    umi
    0.07
    ãĥĪãĥ«
    0.07
     Warn
    0.06
    à¹ģà¸ŀ
    0.06
    overe
    0.06
    avern
    0.06
    cyan
    0.06
     Zen
    0.06
    als
    0.06
    Activations Density 0.000%

    No Known Activations