© 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. 30214
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health statistics and issues

    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
    ØŃت
    -0.06
    _HOOK
    -0.06
     dub
    -0.06
    ока
    -0.06
     peÅŁ
    -0.06
    asca
    -0.06
    iao
    -0.06
    orpion
    -0.05
    еÑģÑĮ
    -0.05
    OSE
    -0.05
    POSITIVE LOGITS
     jadx
    0.07
    jian
    0.06
    aru
    0.06
    BCM
    0.06
    ayas
    0.06
    nici
    0.06
    avar
    0.06
    uis
    0.06
    rente
    0.06
    bc
    0.06
    Activations Density 0.038%

    No Known Activations