© 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. 74162
    Prev
    Next
    INDEX
    Explanations

    subjective expressions or first-person narrative descriptions

    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
    िà¤
    -0.07
     ---------------------------------------------------------------------------↵
    -0.07
    Ïĩε
    -0.07
    ÙĩÙĨ
    -0.07
    owan
    -0.07
    oward
    -0.07
    ederation
    -0.07
    اظ
    -0.07
    this
    -0.07
    IRCLE
    -0.07
    POSITIVE LOGITS
    unto
    0.09
    ina
    0.08
    INA
    0.08
     again
    0.06
    338
    0.06
    Ñĸна
    0.06
    ise
    0.06
    caught
    0.06
    after
    0.06
    218
    0.06
    Activations Density 0.025%

    No Known Activations