© 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. 71390
    Prev
    Next
    INDEX
    Explanations

    numerical values related to scores and weights in a competitive context

    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
    aber
    -0.07
    andr
    -0.07
    inka
    -0.07
    irl
    -0.06
    inkle
    -0.06
    оди
    -0.06
    icha
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    оÑĢож
    -0.06
    omore
    -0.06
    POSITIVE LOGITS
    bron
    0.06
    koli
    0.06
    agine
    0.06
     whereas
    0.06
    orns
    0.06
     à¤ħपर
    0.06
    ucht
    0.06
     Rudd
    0.06
    uç
    0.06
     compared
    0.06
    Activations Density 0.011%

    No Known Activations