© 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. 86391
    Prev
    Next
    INDEX
    Explanations

    references to charitable initiatives and donations

    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
    ãĥ³ãĥĩ
    -0.07
    abeth
    -0.07
    олж
    -0.07
    interop
    -0.07
    Inlining
    -0.06
    ottage
    -0.06
    usercontent
    -0.06
    enes
    -0.06
    oji
    -0.06
     fé
    -0.06
    POSITIVE LOGITS
     organisations
    0.08
     organizations
    0.08
     votes
    0.07
     chooses
    0.07
     charities
    0.07
     chose
    0.07
     decision
    0.07
    .choose
    0.07
     funds
    0.07
     recipient
    0.07
    Activations Density 0.002%

    No Known Activations