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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 97350
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or similes

    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
    reau
    -0.06
    æ
    -0.06
    leys
    -0.06
    -spot
    -0.06
    meno
    -0.06
    mel
    -0.06
    ersen
    -0.06
     $č↵
    -0.06
    apa
    -0.05
    men
    -0.05
    POSITIVE LOGITS
    олÑı
    0.07
    issant
    0.07
    ladu
    0.07
    laz
    0.07
    öz
    0.06
    ãĥ³ãĤº
    0.06
     váºŃy
    0.06
    osate
    0.06
     gü
    0.06
    quam
    0.06
    Activations Density 0.012%

    No Known Activations