© 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. 84595
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming or coding modifications

    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
    vs
    -0.06
    sey
    -0.06
    chine
    -0.06
    urator
    -0.06
     accessory
    -0.06
    uya
    -0.06
    fd
    -0.06
    avel
    -0.05
    segue
    -0.05
     vents
    -0.05
    POSITIVE LOGITS
     replace
    0.10
     Replace
    0.10
    _replace
    0.10
     REPLACE
    0.10
     replaces
    0.10
    .Replace
    0.09
     replacing
    0.09
    .replace
    0.09
     replaced
    0.09
    .replaceAll
    0.09
    Activations Density 0.025%

    No Known Activations