© 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. 15-LLAMASCOPE-RES-131K
    11. 88440
    Prev
    Next
    INDEX
    Explanations

    personal expressions of experiences and feelings

    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
    baÅŁ
    -0.07
    ernals
    -0.07
     ÐĿÑĥ
    -0.07
    kuk
    -0.07
    ÏĦÏĤ
    -0.07
    _firestore
    -0.06
     oku
    -0.06
    vla
    -0.06
    hora
    -0.06
    .Undef
    -0.06
    POSITIVE LOGITS
     not
    0.15
     neither
    0.14
     niet
    0.14
     không
    0.14
     tidak
    0.14
     не
    0.13
     nicht
    0.13
     ikke
    0.12
     no
    0.12
     doesn
    0.12
    Activations Density 0.012%

    No Known Activations