© 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. 40202
    Prev
    Next
    INDEX
    Explanations

    the presence of commas in structured writing

    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
    .amazonaws
    -0.07
    annies
    -0.07
    çļĦæĺ¯
    -0.06
    ÅĦ
    -0.06
    еÑĢжав
    -0.06
    ife
    -0.06
    PELL
    -0.06
    Kn
    -0.06
    gens
    -0.06
    ouro
    -0.06
    POSITIVE LOGITS
    /cat
    0.07
    .opendaylight
    0.07
     whom
    0.06
     SUPER
    0.06
    dek
    0.06
    λιά
    0.06
    iage
    0.06
    ackbar
    0.06
     Which
    0.06
    ÑĥÑģ
    0.06
    Activations Density 0.015%

    No Known Activations