© 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. 17-LLAMASCOPE-RES-131K
    11. 55963
    Prev
    Next
    INDEX
    Explanations

    instances of the word "foreach" indicating iteration 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
    umm
    -0.08
    iffin
    -0.07
    .synthetic
    -0.07
    cae
    -0.07
    zig
    -0.07
    ummer
    -0.07
    /respond
    -0.07
     ucwords
    -0.06
     Thorn
    -0.06
    adır
    -0.06
    POSITIVE LOGITS
    tures
    0.07
    (es
    0.06
    yling
    0.06
    ness
    0.06
    oenix
    0.06
    quiv
    0.06
    most
    0.06
    æł·
    0.06
    süz
    0.06
    LastError
    0.06
    Activations Density 0.002%

    No Known Activations