© 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. 87525
    Prev
    Next
    INDEX
    Explanations

    aspects of creative freedom and collaboration

    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
    optera
    -0.07
    coe
    -0.07
    ocre
    -0.07
    umann
    -0.06
    isclosed
    -0.06
    çIJĨ
    -0.06
     Germ
    -0.06
    uman
    -0.06
    _marshall
    -0.06
    unic
    -0.06
    POSITIVE LOGITS
     freedom
    0.17
     Freedom
    0.13
     freedoms
    0.13
     liberty
    0.13
    Freedom
    0.13
     Ñģвоб
    0.13
    èĩªçĶ±
    0.12
    fre
    0.12
     autonomy
    0.11
     freely
    0.11
    Activations Density 0.053%

    No Known Activations