© 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. 125757
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate user instructions or guidance

    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
    غÙĦ
    -0.06
    omics
    -0.06
    agos
    -0.06
    ceph
    -0.06
    udi
    -0.06
    éĻ£
    -0.06
    ellas
    -0.06
    icit
    -0.06
     Wel
    -0.06
    iec
    -0.05
    POSITIVE LOGITS
    ernen
    0.07
    erap
    0.07
    -hooks
    0.07
     porr
    0.07
     faiz
    0.06
     Err
    0.06
    _INCLUDE
    0.06
    ocz
    0.06
    plusplus
    0.06
    _ES
    0.06
    Activations Density 0.001%

    No Known Activations