© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56576
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and phrases related to connection or addition

    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
     Rosenstein
    -0.08
    ials
    -0.07
    itchen
    -0.07
    ÅŁk
    -0.07
    .habbo
    -0.06
    iere
    -0.06
    ÅĻeh
    -0.06
    .inline
    -0.06
    ingen
    -0.06
    allo
    -0.06
    POSITIVE LOGITS
     permission
    0.07
     access
    0.07
     Vers
    0.07
    icros
    0.07
     assistance
    0.06
     increased
    0.06
     appropriate
    0.06
    ignment
    0.06
     a
    0.06
     adequate
    0.06
    Activations Density 0.040%

    No Known Activations