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

    Neuronpedia

    APICircuit 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. 9-LLAMASCOPE-RES-32K
    6. 21330
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to dependencies in programming and software architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meer
    -0.16
    å´İ
    -0.16
    .EventQueue
    -0.15
    shape
    -0.15
    reed
    -0.14
    rm
    -0.14
    dry
    -0.14
    bone
    -0.14
    ISR
    -0.14
    eno
    -0.14
    POSITIVE LOGITS
    âm
    0.17
    497
    0.16
     toc
    0.15
    ç¿°
    0.14
    審
    0.14
    εÏĨ
    0.14
    ylon
    0.14
     Dalton
    0.14
    _mD
    0.14
    /conf
    0.14
    Activations Density 0.025%

    No Known Activations