© 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. 15-LLAMASCOPE-RES-131K
    11. 86543
    Prev
    Next
    INDEX
    Explanations

    phrases related to what is being communicated and the manner of communication

    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
    umph
    -0.07
    ãĤĴéĸĭ
    -0.07
    ymi
    -0.07
    oger
    -0.07
    .nlm
    -0.06
    emap
    -0.06
    /Dk
    -0.06
    Łèĥ½
    -0.06
    oot
    -0.06
    ikt
    -0.06
    POSITIVE LOGITS
    -src
    0.07
    antz
    0.06
     timing
    0.06
     done
    0.06
     manner
    0.06
    recht
    0.06
     tim
    0.06
     ca
    0.06
     Sadd
    0.06
    _SRC
    0.06
    Activations Density 0.126%

    No Known Activations