© 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. 83097
    Prev
    Next
    INDEX
    Explanations

    the closing brace syntax used in programming code

    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
    za
    -0.07
    ahn
    -0.06
    edic
    -0.06
    alen
    -0.06
    outer
    -0.06
    apps
    -0.06
    umat
    -0.06
    steen
    -0.06
    enia
    -0.06
    ajor
    -0.06
    POSITIVE LOGITS
    ãĥĨãĥ«
    0.07
    696
    0.07
    HasBeenSet
    0.07
     Washing
    0.07
    CEL
    0.07
    .wx
    0.06
    nez
    0.06
     ÑģÑĤаÑĢа
    0.06
    _hub
    0.06
    ÙĦات
    0.06
    Activations Density 0.000%

    No Known Activations