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. 25-LLAMASCOPE-RES-32K
    6. 22804
    Prev
    Next
    INDEX
    Explanations

    mentions of missiles and nuclear weapons related to Iran

    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
    .gz
    -0.17
     PATCH
    -0.15
    PATCH
    -0.15
     addslashes
    -0.15
    patches
    -0.14
    esco
    -0.14
    .scalablytyped
    -0.14
    quette
    -0.14
    .dy
    -0.14
    fos
    -0.14
    POSITIVE LOGITS
     enrichment
    0.30
     enrich
    0.29
     enriched
    0.26
     centrif
    0.26
     plut
    0.26
    uran
    0.24
     uranium
    0.23
     fiss
    0.22
     Uran
    0.21
     Nat
    0.21
    Activations Density 0.010%

    No Known Activations