© 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. 72639
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating expectation or probability

    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
    tit
    -0.07
    aki
    -0.06
    isu
    -0.06
    oran
    -0.06
    ManagedObject
    -0.06
    arf
    -0.05
    oni
    -0.05
    gi
    -0.05
    onec
    -0.05
    길
    -0.05
    POSITIVE LOGITS
    ade
    0.08
    ndon
    0.07
    ç¦
    0.07
    IPA
    0.07
    ych
    0.07
    utr
    0.07
    ela
    0.07
    harma
    0.06
    Ø°
    0.06
    SYNC
    0.06
    Activations Density 0.008%

    No Known Activations