© 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. 15-LLAMASCOPE-RES-131K
    11. 1133
    Prev
    Next
    INDEX
    Explanations

    notations about restrictions or prohibitions

    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
    esan
    -0.08
    adier
    -0.07
    zym
    -0.06
    itone
    -0.06
    plings
    -0.06
    ungi
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    esy
    -0.06
    elf
    -0.06
    iaz
    -0.06
    POSITIVE LOGITS
    //{{
    0.08
    ascus
    0.07
    ICODE
    0.07
    OLON
    0.07
    طع
    0.06
    ocode
    0.06
    ิà¸Ļà¸Ķ
    0.06
    544
    0.06
     direct
    0.06
    602
    0.06
    Activations Density 0.002%

    No Known Activations