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. 30-LLAMASCOPE-RES-32K
    6. 23461
    Prev
    Next
    INDEX
    Explanations

    terms related to the physiological effects and functions of the liver and digestive system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Injector
    -0.17
    ÐIJÑĢÑħÑĸв
    -0.16
    aho
    -0.15
    haf
    -0.15
    aad
    -0.14
    ebo
    -0.14
    odon
    -0.14
    stash
    -0.14
    ignum
    -0.14
    xad
    -0.13
    POSITIVE LOGITS
     digestive
    0.38
     digestion
    0.37
     digest
    0.37
     intestinal
    0.36
     stomach
    0.36
     Digest
    0.34
     gut
    0.34
     dig
    0.33
     intest
    0.33
     intestine
    0.33
    Activations Density 0.042%

    No Known Activations