© 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. 27036
    Prev
    Next
    INDEX
    Explanations

    the presence of sentences or significant punctuation

    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
    _gem
    -0.07
    äº
    -0.06
     Hanson
    -0.06
     bonded
    -0.06
    (Me
    -0.06
     favourite
    -0.06
    nze
    -0.06
     Ä
    -0.06
     dik
    -0.06
    彦
    -0.06
    POSITIVE LOGITS
    ague
    0.07
    umu
    0.07
    PCODE
    0.07
    uke
    0.07
    racat
    0.06
    habi
    0.06
    Ðĩ
    0.06
    ế
    0.06
    unas
    0.06
    alic
    0.06
    Activations Density 0.000%

    No Known Activations