© 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. 125597
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recognition or notoriety of individuals or entities

    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
    afort
    -0.08
    amon
    -0.08
    quat
    -0.07
    anol
    -0.07
    ivent
    -0.07
    amber
    -0.07
    cad
    -0.07
    cust
    -0.07
    iyah
    -0.07
    quare
    -0.07
    POSITIVE LOGITS
     pseud
    0.07
     rever
    0.06
    lea
    0.06
     trough
    0.06
    _formats
    0.06
     familiar
    0.06
     alias
    0.05
     who
    0.05
     name
    0.05
    byname
    0.05
    Activations Density 0.005%

    No Known Activations