© 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 EvalsExportsinterp-engineNEWAPI 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. 70271
    Prev
    Next
    INDEX
    Explanations

    phrases related to age and demographic 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
    zano
    -0.07
    agini
    -0.07
    rane
    -0.06
    ·æĸ°
    -0.06
    staking
    -0.06
    amen
    -0.06
    abis
    -0.06
    سات
    -0.06
    raci
    -0.06
    shi
    -0.06
    POSITIVE LOGITS
    _stderr
    0.08
     (<
    0.07
     age
    0.07
     peak
    0.06
    ục
    0.06
    ippers
    0.06
    воз
    0.06
    _iff
    0.06
     sos
    0.05
    ibar
    0.05
    Activations Density 0.007%

    No Known Activations