© 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. 75308
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "with" in various contexts

    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
    ê°ľë¥¼
    -0.08
    ÏħÏĦÏĮ
    -0.08
    ãĥ©ãĤ¤ãĥĪ
    -0.08
    ä¹İ
    -0.08
     무ìĹĩ
    -0.08
    ÐłÐĿ
    -0.08
    plevel
    -0.08
    avit
    -0.08
     vfs
    -0.07
    iterals
    -0.07
    POSITIVE LOGITS
     whom
    0.11
     whose
    0.08
     who
    0.07
     disabilities
    0.07
     access
    0.07
     valid
    0.07
    stood
    0.06
     similar
    0.06
    whose
    0.06
     experience
    0.06
    Activations Density 0.020%

    No Known Activations