© 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. 124721
    Prev
    Next
    INDEX
    Explanations

    mentions of Facebook and its functionalities

    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
    emet
    -0.08
    Ñĩин
    -0.07
    aga
    -0.07
    iat
    -0.07
     Wong
    -0.06
    rollo
    -0.06
    prus
    -0.06
     Dans
    -0.06
    _firestore
    -0.06
    gal
    -0.06
    POSITIVE LOGITS
    âĢŀM
    0.08
     platform
    0.08
    âĢŀP
    0.08
    алÑĭ
    0.08
     target
    0.07
    cia
    0.07
     targeting
    0.07
    âĢŀV
    0.07
    241
    0.07
    ForResource
    0.07
    Activations Density 0.010%

    No Known Activations