© 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. 55884
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    hci
    -0.07
    ãĤ¹ãĤ¯
    -0.07
     poil
    -0.07
     kli
    -0.07
    _RB
    -0.07
    avig
    -0.07
    ÑģÑĮ
    -0.07
    озем
    -0.07
    οÏįν
    -0.07
    782
    -0.07
    POSITIVE LOGITS
    /stdc
    0.07
     Already
    0.06
    Already
    0.06
    AGMA
    0.06
     unsubscribe
    0.06
    zel
    0.06
     plus
    0.06
    IBC
    0.05
    'gc
    0.05
     HG
    0.05
    Activations Density 0.010%

    No Known Activations