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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61137
    Prev
    Next
    INDEX
    Explanations

    references to spatial layouts and measurements

    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
    ilden
    -0.08
    ãĤ¤ãĥ³ãĥĪ
    -0.08
    olit
    -0.07
    uds
    -0.07
    isd
    -0.07
    ingleton
    -0.07
    voir
    -0.07
    CONF
    -0.07
    lyph
    -0.07
    hci
    -0.07
    POSITIVE LOGITS
     territory
    0.09
     prime
    0.07
     airspace
    0.06
     portions
    0.06
     portion
    0.06
     space
    0.06
     plain
    0.06
     turf
    0.06
     land
    0.06
     coastline
    0.06
    Activations Density 0.065%

    No Known Activations