© 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 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. 88246
    Prev
    Next
    INDEX
    Explanations

    words associated with bending or curvature

    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
    onet
    -0.08
    iego
    -0.08
    GROUND
    -0.07
    abama
    -0.07
    conscious
    -0.07
    ground
    -0.07
     جÙĦ
    -0.07
    erap
    -0.07
    ä¹±
    -0.07
    imen
    -0.07
    POSITIVE LOGITS
     bend
    0.07
     bends
    0.07
     bending
    0.07
     Bend
    0.07
     bent
    0.07
    backs
    0.07
    y
    0.06
    ToFit
    0.06
    uling
    0.06
    /stretch
    0.06
    Activations Density 0.025%

    No Known Activations