© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118444
    Prev
    Next
    INDEX
    Explanations

    expressions indicating prevalence or frequency

    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
    ZONE
    -0.07
    ữ
    -0.07
    uka
    -0.07
    apel
    -0.07
    zone
    -0.07
    ån
    -0.07
    sta
    -0.07
     Tune
    -0.07
    ritt
    -0.07
    igation
    -0.07
    POSITIVE LOGITS
    ledo
    0.07
    chie
    0.07
    leet
    0.06
    chers
    0.06
    Signature
    0.06
    ãģĵãģĿ
    0.06
     mun
    0.06
    ahat
    0.06
     Fav
    0.05
     disag
    0.05
    Activations Density 0.001%

    No Known Activations