© 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. 17-LLAMASCOPE-RES-131K
    11. 57808
    Prev
    Next
    INDEX
    Explanations

    descriptions of trails and paths

    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
     seas
    -0.07
     sông
    -0.06
    æ¼
    -0.06
     oceans
    -0.06
     lakes
    -0.06
    rig
    -0.06
    lake
    -0.06
    lut
    -0.06
    pps
    -0.06
    897
    -0.06
    POSITIVE LOGITS
     path
    0.10
     paths
    0.10
     trail
    0.09
    -path
    0.08
     Path
    0.08
    è·¯å¾Ħ
    0.08
     track
    0.08
    path
    0.08
     Paths
    0.08
     Track
    0.07
    Activations Density 0.018%

    No Known Activations