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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17609
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular biology and the effects of compounds on cells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é©
    -0.14
    UIApplication
    -0.14
    gın
    -0.14
    åī
    -0.14
     Modifier
    -0.13
    ALSE
    -0.13
     Bale
    -0.13
    ny
    -0.13
    ĶĦ
    -0.13
    tra
    -0.13
    POSITIVE LOGITS
     apoptosis
    0.29
     apopt
    0.25
     cas
    0.23
     proliferation
    0.22
     Migration
    0.20
     DNA
    0.19
     migration
    0.19
     viability
    0.19
     cell
    0.18
     activations
    0.17
    Activations Density 0.107%

    No Known Activations