© 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 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. 85323
    Prev
    Next
    INDEX
    Explanations

    phrases related to location and proximity

    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
    EDIA
    -0.06
    lio
    -0.06
     åį
    -0.06
    pte
    -0.06
    .mk
    -0.06
    ῶν
    -0.06
    udas
    -0.06
     dette
    -0.06
    çĸ
    -0.06
    ori
    -0.05
    POSITIVE LOGITS
    ÅĻev
    0.07
    ÅĻÃŃt
    0.07
     migrationBuilder
    0.06
    ecast
    0.06
    imos
    0.06
    reshold
    0.06
     prol
    0.06
    रण
    0.06
    ereum
    0.06
    ancode
    0.06
    Activations Density 0.000%

    No Known Activations