© 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. 57083
    Prev
    Next
    INDEX
    Explanations

    references to years and numerical data in the text

    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
    .heroku
    -0.07
    erece
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    .sourceforge
    -0.06
     [[]
    -0.06
    รม
    -0.06
    .cut
    -0.06
    asc
    -0.06
     point
    -0.06
     verified
    -0.06
    POSITIVE LOGITS
    ropa
    0.07
    neau
    0.07
    andle
    0.07
    ning
    0.06
     Analog
    0.06
    ilig
    0.06
    asset
    0.06
    iche
    0.06
    otte
    0.06
    icha
    0.06
    Activations Density 0.013%

    No Known Activations