© 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. 57598
    Prev
    Next
    INDEX
    Explanations

    phrases related to licenses and legal permissions

    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
    less
    -0.06
    ington
    -0.06
     meat
    -0.06
    anie
    -0.06
    ify
    -0.06
    ìĭ¤
    -0.06
    ress
    -0.05
     Davidson
    -0.05
    oad
    -0.05
    ons
    -0.05
    POSITIVE LOGITS
    .Remote
    0.08
    ģ
    0.08
    sı
    0.08
    .esp
    0.07
     puan
    0.07
    cü
    0.07
    utenberg
    0.07
     plá
    0.07
    -describedby
    0.07
    actionDate
    0.07
    Activations Density 0.001%

    No Known Activations