© 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. 15-LLAMASCOPE-RES-131K
    11. 26823
    Prev
    Next
    INDEX
    Explanations

    specific keywords that denote significant places or titles in various contexts

    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
    rors
    -0.06
    itech
    -0.06
    ÑĢÑĥÑĩ
    -0.06
    apa
    -0.06
    istics
    -0.06
    å¤ķ
    -0.06
    оÑī
    -0.06
    weise
    -0.06
    example
    -0.06
     alike
    -0.06
    POSITIVE LOGITS
    Ïĥμα
    0.07
    ndef
    0.07
    enda
    0.07
    /Gate
    0.07
    iran
    0.06
    ìĭľìĺ¤
    0.06
    ATRIX
    0.06
    çĺ
    0.06
    473
    0.06
     nuest
    0.06
    Activations Density 0.045%

    No Known Activations