© 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. 88797
    Prev
    Next
    INDEX
    Explanations

    variations of the word "achieve" or related successful completion terms

    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
    IRROR
    -0.07
    ocio
    -0.07
    nard
    -0.07
    istrat
    -0.06
    ickle
    -0.06
    mür
    -0.06
    chief
    -0.06
    Å¡en
    -0.06
    berman
    -0.06
    prit
    -0.06
    POSITIVE LOGITS
    pis
    0.07
    rames
    0.07
    £p
    0.06
    CTS
    0.06
     Guth
    0.06
     tend
    0.06
    stime
    0.06
    ulty
    0.05
    swith
    0.05
     and
    0.05
    Activations Density 0.000%

    No Known Activations