© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61908
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate choice or preference

    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
    egl
    -0.07
    ç
    -0.07
    ignum
    -0.07
     Latitude
    -0.07
    EdgeInsets
    -0.06
    osg
    -0.06
    addon
    -0.06
    uess
    -0.06
    ียà¸Ļ
    -0.06
     Lever
    -0.06
    POSITIVE LOGITS
    bole
    0.07
    isans
    0.07
    kers
    0.07
     Χα
    0.06
    472
    0.06
    istrovstvÃŃ
    0.06
    ramid
    0.06
    mage
    0.06
    rome
    0.06
     fancy
    0.06
    Activations Density 0.005%

    No Known Activations