© 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 EvalsExportsinterp-engineNEWAPI 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. 120128
    Prev
    Next
    INDEX
    Explanations

    directional verbs and phrases related to navigation

    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
    ceae
    -0.07
    exampleInputEmail
    -0.07
    RING
    -0.07
     Meadow
    -0.06
    inction
    -0.06
     sym
    -0.06
    ÑĨÑı
    -0.06
    airy
    -0.06
    earer
    -0.06
    vincial
    -0.06
    POSITIVE LOGITS
     compass
    0.07
     direction
    0.06
    itta
    0.06
    itten
    0.06
    oll
    0.06
    notated
    0.06
    prak
    0.06
    compass
    0.06
    éī
    0.06
     Tob
    0.06
    Activations Density 0.008%

    No Known Activations