© 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. 74946
    Prev
    Next
    INDEX
    Explanations

    numerical data related to homelessness and temporary accommodation statistics

    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
    resh
    -0.06
     adoption
    -0.05
    igate
    -0.05
    aign
    -0.05
     sigh
    -0.05
    igli
    -0.05
     SEQ
    -0.05
     serial
    -0.05
     me
    -0.05
     till
    -0.05
    POSITIVE LOGITS
    ((__
    0.08
    ByKey
    0.08
    सर
    0.08
    _fu
    0.07
    pek
    0.07
    ãģĸ
    0.07
    imas
    0.07
     bordel
    0.07
    ÑģÑĭ
    0.07
    .ibm
    0.07
    Activations Density 0.008%

    No Known Activations