© 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. 17-LLAMASCOPE-RES-131K
    11. 130322
    Prev
    Next
    INDEX
    Explanations

    concepts related to different pathways or directions in life

    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
    ucz
    -0.07
    rud
    -0.07
    ække
    -0.06
    agine
    -0.06
    ece
    -0.06
    ndl
    -0.06
    /Index
    -0.06
    ringe
    -0.06
    aits
    -0.06
    stu
    -0.06
    POSITIVE LOGITS
     path
    0.18
     paths
    0.15
    path
    0.14
    -path
    0.14
     Path
    0.14
     Paths
    0.13
    .path
    0.13
    è·¯å¾Ħ
    0.13
     è·¯
    0.12
     pathway
    0.12
    Activations Density 0.046%

    No Known Activations