© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94430
    Prev
    Next
    INDEX
    Explanations

    sequences of definite articles used in various contexts

    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
     mys
    -0.06
    se
    -0.06
     Masc
    -0.06
     pau
    -0.05
     Defined
    -0.05
     Brewer
    -0.05
     Lage
    -0.05
     defs
    -0.05
    Æł
    -0.05
    ii
    -0.05
    POSITIVE LOGITS
    kem
    0.09
    ahlen
    0.08
    ulin
    0.07
     Bernardino
    0.07
    /stdc
    0.07
     ;č↵
    0.07
    enga
    0.07
    fsp
    0.07
    ORS
    0.07
    itches
    0.07
    Activations Density 0.059%

    No Known Activations