Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61074
    Prev
    Next
    INDEX
    Explanations

    terms related to breeding and population dynamics

    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
    marshall
    -0.07
     Pall
    -0.06
     Burl
    -0.06
    hw
    -0.06
     moll
    -0.06
    ware
    -0.06
     Gran
    -0.06
    lod
    -0.06
    raki
    -0.06
     tarihli
    -0.06
    POSITIVE LOGITS
     genetics
    0.07
     sire
    0.07
    aits
    0.07
     Genetic
    0.07
    -toolbar
    0.07
     semen
    0.07
    atab
    0.07
     studs
    0.06
     Selection
    0.06
    ìľ¡
    0.06
    Activations Density 0.002%

    No Known Activations