© 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. 126924
    Prev
    Next
    INDEX
    Explanations

    titles and sections of academic or informative texts

    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
    itch
    -0.07
    rve
    -0.07
    929
    -0.06
    ree
    -0.06
    oka
    -0.06
    ullo
    -0.06
    conn
    -0.06
    leave
    -0.06
    ptune
    -0.06
    ull
    -0.06
    POSITIVE LOGITS
     بÙĪابة
    0.07
    &o
    0.07
     Abram
    0.06
    تÙĬÙĨ
    0.06
    datagrid
    0.06
     Interrupt
    0.06
    ParameterValue
    0.06
    apı
    0.06
    ìĿij
    0.06
     Lover
    0.06
    Activations Density 0.024%

    No Known Activations