© 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. 92834
    Prev
    Next
    INDEX
    Explanations

    references to consumer protection and scams related to disaster relief efforts

    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
    afone
    -0.08
    umpt
    -0.07
    rix
    -0.07
    ienen
    -0.07
    ruk
    -0.07
    ymb
    -0.07
    usty
    -0.06
    chant
    -0.06
    =search
    -0.06
     distort
    -0.06
    POSITIVE LOGITS
     contributions
    0.09
     contribution
    0.09
    Contrib
    0.09
    -contrib
    0.08
    contrib
    0.08
     pÅĻisp
    0.08
     Contribution
    0.07
     contributing
    0.07
     contribute
    0.07
    _contrib
    0.07
    Activations Density 0.021%

    No Known Activations