© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61583
    Prev
    Next
    INDEX
    Explanations

    terms related to national identity and organizational structure in a sporting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Placeholder tokens in technical documentation and code samples that indicate variables, parameters, or values to be substituted by users when implementing commands or functions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ii
    -0.06
    ibold
    -0.06
     prior
    -0.06
    endi
    -0.06
     ÙĩÙĨ
    -0.06
    .GridView
    -0.06
    rid
    -0.06
    erv
    -0.06
    _:*
    -0.06
    ifar
    -0.06
    POSITIVE LOGITS
    enga
    0.07
    esan
    0.07
    name
    0.07
    _you
    0.07
    FFECT
    0.07
    Nm
    0.07
    rien
    0.07
    iag
    0.06
    AtA
    0.06
    eyin
    0.06
    Activations Density 0.065%

    No Known Activations