© 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. 15-LLAMASCOPE-RES-131K
    6. 61736
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly those related to individuals or specific entities

    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
    زÙĦ
    -0.07
    ιακ
    -0.07
    osphere
    -0.07
    .sym
    -0.07
    ibi
    -0.07
    asje
    -0.06
    اشت
    -0.06
    asm
    -0.06
    isphere
    -0.06
    ecs
    -0.06
    POSITIVE LOGITS
     ÑĥлÑĭ
    0.06
    rou
    0.06
     Bale
    0.06
    aterno
    0.06
    [email
    0.06
     Lud
    0.06
    embro
    0.06
     Fiona
    0.05
    anta
    0.05
    462
    0.05
    Activations Density 0.003%

    No Known Activations