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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128984
    Prev
    Next
    INDEX
    Explanations

    terms related to simplicity and simplification

    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
    riel
    -0.09
    ampler
    -0.07
    inous
    -0.07
    ngr
    -0.07
     Demir
    -0.07
    veled
    -0.07
    esimal
    -0.07
    lers
    -0.06
    orical
    -0.06
    quin
    -0.06
    POSITIVE LOGITS
    tons
    0.14
    ton
    0.12
    -minded
    0.12
    xes
    0.12
     minded
    0.11
    st
    0.10
    ctic
    0.09
    /simple
    0.08
    TON
    0.08
     Minds
    0.08
    Activations Density 0.027%

    No Known Activations