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. 29-LLAMASCOPE-RES-32K
    6. 13888
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Li" and its variations, indicating a focus on licenses or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riend
    -0.16
     Tall
    -0.15
     arbit
    -0.15
     меÑĢе
    -0.15
    chema
    -0.15
    ibt
    -0.15
    ord
    -0.14
    chemas
    -0.14
    bat
    -0.14
    ulas
    -0.14
    POSITIVE LOGITS
    uzzi
    0.18
    ens
    0.17
    ées
    0.16
    kas
    0.15
     separat
    0.15
    _hyper
    0.15
    γÏī
    0.15
    OfClass
    0.15
    ến
    0.14
     пÑĢоÑĩ
    0.14
    Activations Density 0.002%

    No Known Activations