© 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. 22-LLAMASCOPE-RES-131K
    11. 4130
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements in text

    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
    анка
    -0.07
    aca
    -0.07
    Andy
    -0.07
    eme
    -0.06
    Ãłu
    -0.06
    ACA
    -0.06
    iami
    -0.06
     SUN
    -0.06
     Cair
    -0.06
    енÑĮ
    -0.06
    POSITIVE LOGITS
    56
    0.14
    55
    0.14
    54
    0.13
    57
    0.13
    53
    0.12
    51
    0.11
    59
    0.11
     Fifty
    0.11
    52
    0.11
    155
    0.10
    Activations Density 0.044%

    No Known Activations