© 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. 17-LLAMASCOPE-RES-131K
    6. 74657
    Prev
    Next
    INDEX
    Explanations

    professional titles and qualifications related to legal professionals

    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
    aldi
    -0.07
    uits
    -0.06
     Pillow
    -0.06
    iasi
    -0.06
    éo
    -0.06
    (strtolower
    -0.06
    ibs
    -0.06
    mae
    -0.06
    osl
    -0.06
    ninger
    -0.06
    POSITIVE LOGITS
     migrationBuilder
    0.09
    anson
    0.07
    ä¸Ģ页
    0.06
    ิà¹Ģศษ
    0.06
    senal
    0.06
    OperationException
    0.06
    ICA
    0.06
    prite
    0.06
    .const
    0.06
    606
    0.06
    Activations Density 0.002%

    No Known Activations