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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-32K
    6. 6138
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ëĦIJ
    -0.16
     reopening
    -0.13
    _REUSE
    -0.13
     cooperating
    -0.13
    .scalablytyped
    -0.13
    utenberg
    -0.13
    IFIED
    -0.13
     createContext
    -0.13
    641
    -0.12
    endent
    -0.12
    POSITIVE LOGITS
     grew
    0.42
     growing
    0.33
     graduated
    0.30
     grown
    0.29
     Growing
    0.29
    Growing
    0.28
     attended
    0.27
     studied
    0.27
     hail
    0.27
     grow
    0.27
    Activations Density 0.171%

    No Known Activations