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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 6131
    Prev
    Next
    INDEX
    Explanations

    types of drugs and their potential effects on the brain and body

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exclusive
    -0.14
    emin
    -0.14
    plied
    -0.14
    /cards
    -0.14
    ModelState
    -0.13
    420
    -0.13
    aday
    -0.13
    diamond
    -0.13
    uliar
    -0.13
    loit
    -0.13
    POSITIVE LOGITS
    ics
    0.17
     such
    0.17
     SUCH
    0.15
     family
    0.15
    rawler
    0.15
    ENCH
    0.15
     ÑĤакими
    0.15
    ÑĢод
    0.14
    ICS
    0.14
    ç¥
    0.14
    Activations Density 0.068%

    No Known Activations