© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125208
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places and people

    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
    ovi
    -0.07
    erea
    -0.07
    ansson
    -0.06
    lad
    -0.06
     fatal
    -0.06
    insky
    -0.06
    nell
    -0.06
     inev
    -0.06
    gc
    -0.05
    anyak
    -0.05
    POSITIVE LOGITS
    kke
    0.08
    меж
    0.07
    spÄĽ
    0.07
    quare
    0.07
    ÑĪев
    0.07
    .decorate
    0.07
     å¹³æĸ¹
    0.07
    _IPV
    0.06
    IMIT
    0.06
    hlas
    0.06
    Activations Density 0.036%

    No Known Activations