© 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. 108210
    Prev
    Next
    INDEX
    Explanations

    measures of distance, specifically kilometers and related units

    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
    eden
    -0.07
    ernal
    -0.07
    inned
    -0.06
    lessly
    -0.06
    yd
    -0.06
    &P
    -0.06
    room
    -0.06
    sy
    -0.06
    ç³»
    -0.06
    lh
    -0.06
    POSITIVE LOGITS
    -long
    0.12
    -wide
    0.10
    ètres
    0.09
    eters
    0.07
    rades
    0.07
     radius
    0.07
    itters
    0.07
    adiens
    0.07
    -high
    0.07
    -length
    0.06
    Activations Density 0.010%

    No Known Activations