© 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. 56513
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their experiences or actions

    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
    IMIT
    -0.07
    ehr
    -0.07
    ulg
    -0.07
    enville
    -0.07
    oby
    -0.06
    ountry
    -0.06
    osg
    -0.06
    herits
    -0.06
    PLUGIN
    -0.06
    reib
    -0.06
    POSITIVE LOGITS
     want
    0.14
     wants
    0.14
     wanted
    0.12
     muá»ijn
    0.12
    want
    0.11
    è¦ģ
    0.11
     Wants
    0.10
     wanting
    0.10
    Want
    0.10
    wanted
    0.10
    Activations Density 0.032%

    No Known Activations