© 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. 29577
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary and function references in programming contexts

    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
    殿
    -0.08
    leh
    -0.07
    ï¿
    -0.07
    isz
    -0.07
    ilm
    -0.07
    noinspection
    -0.06
    egan
    -0.06
    avana
    -0.06
    avage
    -0.06
    ÙĦÙħÙĩ
    -0.06
    POSITIVE LOGITS
    gger
    0.07
     stretch
    0.07
    ("
    0.06
    <typeof
    0.06
    ienes
    0.06
    cak
    0.06
    ulla
    0.06
    illis
    0.06
     Laden
    0.06
    á»ĥn
    0.06
    Activations Density 0.143%

    No Known Activations