© 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. 18299
    Prev
    Next
    INDEX
    Explanations

    causal relationships and conditions related to health 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
    ander
    -0.08
    illac
    -0.07
    strup
    -0.06
    andas
    -0.06
    resher
    -0.06
    agara
    -0.06
     tvar
    -0.06
    eder
    -0.06
    ÙĪÙĬÙĥ
    -0.06
    .KeyChar
    -0.06
    POSITIVE LOGITS
     be
    0.07
     also
    0.06
    ooks
    0.06
    导èĩ´
    0.06
    resents
    0.06
    عاÙĨ
    0.06
    IKE
    0.06
    elen
    0.06
    dba
    0.06
     caused
    0.05
    Activations Density 0.021%

    No Known Activations