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. 22-LLAMASCOPE-RES-32K
    6. 16939
    Prev
    Next
    INDEX
    Explanations

    references to medications and their effects in the context of legal cases related to health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bach
    -0.18
    anke
    -0.18
    anik
    -0.17
    ypass
    -0.15
    steder
    -0.15
    icha
    -0.14
    .sessions
    -0.14
    hek
    -0.14
     Ðŀдна
    -0.14
    outil
    -0.14
    POSITIVE LOGITS
     aspir
    0.40
     ib
    0.31
     NSA
    0.30
     pain
    0.30
     Ib
    0.30
     anal
    0.26
     nap
    0.23
     Pain
    0.23
     headache
    0.22
    pir
    0.22
    Activations Density 0.157%

    No Known Activations