© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105697
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or executing plans

    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
    ruba
    -0.08
    çĪµ
    -0.07
    //{{
    -0.07
    ÑĢÑĸÑĪ
    -0.07
    abbo
    -0.07
    ieber
    -0.07
    fdb
    -0.07
    antz
    -0.07
    αÏģά
    -0.07
    икÑĥ
    -0.07
    POSITIVE LOGITS
     feat
    0.13
     feats
    0.11
     task
    0.09
    heimer
    0.09
     tasks
    0.08
    task
    0.08
    feat
    0.07
     TASK
    0.07
     mission
    0.06
    (task
    0.06
    Activations Density 0.039%

    No Known Activations