© 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. 119235
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize totality or completeness

    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
    orig
    -0.06
    arella
    -0.06
    ycl
    -0.06
     çĨ
    -0.06
    нÑĥв
    -0.06
    htar
    -0.06
    otonin
    -0.06
    adh
    -0.06
    IQ
    -0.06
     capture
    -0.06
    POSITIVE LOGITS
     likelihood
    0.07
     probability
    0.07
    ç£
    0.07
     legisl
    0.06
    ĥn
    0.06
    072
    0.06
    279
    0.06
     Probability
    0.06
    rschein
    0.06
    zik
    0.06
    Activations Density 0.008%

    No Known Activations