© 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. 83220
    Prev
    Next
    INDEX
    Explanations

    occurrences of coordinates and spatial relationships in a technical context

    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
    ATO
    -0.06
    planes
    -0.06
     line
    -0.06
    ή
    -0.06
    idge
    -0.06
     STREET
    -0.06
     walls
    -0.06
    estr
    -0.06
    ?type
    -0.06
     обоÑĢ
    -0.06
    POSITIVE LOGITS
     corner
    0.12
    opleft
    0.10
     corners
    0.09
     centre
    0.09
    corner
    0.09
     center
    0.09
    -corner
    0.09
    :CGPoint
    0.09
     Corner
    0.08
    -center
    0.08
    Activations Density 0.128%

    No Known Activations