© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96256
    Prev
    Next
    INDEX
    Explanations

    references to heartbeat and related concepts, particularly in the context of abortion and life discussions

    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
    adesh
    -0.07
    éļ
    -0.07
    ellen
    -0.07
     Cabr
    -0.07
    ARSER
    -0.07
    pill
    -0.07
    vrier
    -0.07
    vice
    -0.06
    elters
    -0.06
     INCIDENT
    -0.06
    POSITIVE LOGITS
    Reserved
    0.07
    λÎŃ
    0.07
    oras
    0.06
    ixo
    0.06
     Batch
    0.06
    872
    0.06
    ceph
    0.06
    prene
    0.06
    963
    0.06
     Lud
    0.06
    Activations Density 0.001%

    No Known Activations