© 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. 57081
    Prev
    Next
    INDEX
    Explanations

    spatial and location-related information

    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
    анÑĮ
    -0.07
    CEPT
    -0.07
    ulu
    -0.07
    ceiver
    -0.07
    arium
    -0.06
     Armour
    -0.06
     Äij
    -0.06
     Rip
    -0.06
    _lengths
    -0.06
    _UD
    -0.06
    POSITIVE LOGITS
     coordinates
    0.09
     Coordinates
    0.08
     latitude
    0.08
     lat
    0.08
    -lat
    0.08
     Latitude
    0.08
     coords
    0.07
    latitude
    0.07
    lat
    0.07
    coordinates
    0.07
    Activations Density 0.035%

    No Known Activations