© 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. 17-LLAMASCOPE-RES-131K
    11. 56753
    Prev
    Next
    INDEX
    Explanations

    instances of legal or criminal reporting

    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
    ï¿
    -0.08
    Å¡t
    -0.07
    innen
    -0.07
    аниÑĨ
    -0.07
    ordion
    -0.06
    anten
    -0.06
    akis
    -0.06
    маз
    -0.06
    stim
    -0.06
    Streamer
    -0.06
    POSITIVE LOGITS
     biz
    0.07
     probe
    0.07
     info
    0.06
    ãĥ¼ãĤº
    0.06
    CLIENT
    0.06
    _hierarchy
    0.06
     probes
    0.06
    reature
    0.06
     dog
    0.06
    BED
    0.06
    Activations Density 0.014%

    No Known Activations