© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations, indicating a focus on sequential actions or references

    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
    hani
    -0.07
    ottle
    -0.06
    ston
    -0.06
     duck
    -0.06
     Quint
    -0.06
    isko
    -0.06
    /TT
    -0.06
    _motion
    -0.06
    Minute
    -0.06
    éĢĨ
    -0.06
    POSITIVE LOGITS
     followed
    0.10
    follow
    0.08
     preceded
    0.07
     Follow
    0.07
    draul
    0.07
     immediately
    0.06
    igor
    0.06
     ØŃÛĮ
    0.06
    877
    0.06
     sequel
    0.06
    Activations Density 0.014%

    No Known Activations