© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27191
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate degrees of probability and potential outcomes

    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
    ekim
    -0.07
    pei
    -0.06
    ournals
    -0.06
    andest
    -0.06
    uster
    -0.06
    uset
    -0.06
    زÙĦ
    -0.06
    embali
    -0.06
    ebo
    -0.06
     harness
    -0.06
    POSITIVE LOGITS
     chances
    0.17
     chance
    0.16
     likely
    0.16
     likelihood
    0.15
     possibility
    0.14
    likely
    0.13
    likelihood
    0.13
     Likely
    0.12
     веÑĢоÑıÑĤ
    0.12
    åı¯èĥ½æĢ§
    0.12
    Activations Density 0.016%

    No Known Activations