Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5261
    Prev
    Next
    INDEX
    Explanations

    negation statements

    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
    á¿
    -0.07
    ilians
    -0.07
    agas
    -0.07
    unicip
    -0.07
    liga
    -0.06
    issors
    -0.06
    illaume
    -0.06
    istas
    -0.06
    iais
    -0.06
    úi
    -0.06
    POSITIVE LOGITS
     be
    0.17
     být
    0.10
     باشد
    0.09
     бÑĭÑĤÑĮ
    0.08
     become
    0.07
     exceed
    0.07
    è¶ħè¿ĩ
    0.07
    be
    0.07
     byÄĩ
    0.07
    Be
    0.06
    Activations Density 0.015%

    No Known Activations