© 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. 9-LLAMASCOPE-RES-131K
    11. 98476
    Prev
    Next
    INDEX
    Explanations

    phrases related to refusal or denial of information

    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
    eland
    -0.08
    otton
    -0.07
    bers
    -0.07
    rek
    -0.07
    aste
    -0.06
    neau
    -0.06
    iana
    -0.06
    aylor
    -0.06
    berg
    -0.06
     trench
    -0.06
    POSITIVE LOGITS
    YLON
    0.09
    UBY
    0.07
    erif
    0.07
    ÑĤап
    0.07
    ãĥ³ãĥĸ
    0.07
     Duffy
    0.07
     cá»Ń
    0.07
    urette
    0.07
    ifa
    0.07
    rais
    0.07
    Activations Density 0.008%

    No Known Activations