Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5176
    Prev
    Next
    INDEX
    Explanations

    commas in various 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
    ythe
    -0.07
    oret
    -0.07
    itative
    -0.07
     воÑĤ
    -0.07
    inand
    -0.07
    ει
    -0.07
    beit
    -0.06
    and
    -0.06
    –↵↵
    -0.06
    itre
    -0.06
    POSITIVE LOGITS
    201
    0.12
    202
    0.10
    200
    0.08
    Û²Û°Û±
    0.06
    {}
    0.06
    amera
    0.06
    unte
    0.06
    000
    0.06
     jl
    0.06
    cle
    0.05
    Activations Density 0.013%

    No Known Activations