© 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. 9-LLAMASCOPE-RES-131K
    11. 95483
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "making" and activities associated with creation or development

    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
    alysis
    -0.08
    ael
    -0.08
    ities
    -0.07
    ized
    -0.07
     edin
    -0.07
    illac
    -0.07
    ization
    -0.07
    ringe
    -0.06
    scopic
    -0.06
    ativa
    -0.06
    POSITIVE LOGITS
     GetLastError
    0.06
    _Meta
    0.06
    گراÙĨ
    0.06
     iParam
    0.06
    -related
    0.06
    ERO
    0.06
    ECTOR
    0.06
    æ´ĭ
    0.06
    ìļ©
    0.06
    (er
    0.06
    Activations Density 0.046%

    No Known Activations