© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 480
    Prev
    Next
    INDEX
    Explanations

    specific queries or statements about narratives or stories

    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
    akedown
    -0.08
    με
    -0.06
    CRET
    -0.06
    437
    -0.06
    Planet
    -0.06
    RAIN
    -0.06
    .Îķ
    -0.06
    lse
    -0.06
    941
    -0.06
    .toByteArray
    -0.06
    POSITIVE LOGITS
    icode
    0.07
    _Lean
    0.07
    tery
    0.06
    ights
    0.06
     untreated
    0.06
     Beckham
    0.06
    *)((
    0.06
    nard
    0.06
     nonatomic
    0.06
    ãģĿãģĨãģª
    0.06
    Activations Density 0.025%

    No Known Activations