© 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. 73585
    Prev
    Next
    INDEX
    Explanations

    instances of belief or assertions about people's feelings or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Connecting words or phrases that bridge different parts of text, typically prepositions, linking verbs, or transitional elements that establish relationships between ideas.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    zcze
    -0.08
     actionTypes
    -0.07
    uby
    -0.07
     öden
    -0.07
     OnTrigger
    -0.07
    orris
    -0.07
    ÑĢÑĸз
    -0.07
    acons
    -0.07
    fieldname
    -0.07
     Spit
    -0.06
    POSITIVE LOGITS
    447
    0.07
     –
    0.06
     "
    0.06
     “
    0.06
    ÅŁiv
    0.05
    345
    0.05
    @NgModule
    0.05
    ADDE
    0.05
    IRMWARE
    0.05
    unfinished
    0.05
    Activations Density 0.049%

    No Known Activations