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. 4-LLAMASCOPE-RES-32K
    6. 2476
    Prev
    Next
    INDEX
    Explanations

    references to keys and key-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ple
    -0.16
    èĢħãģ®
    -0.15
    FromClass
    -0.15
    -routing
    -0.15
    iah
    -0.15
    eba
    -0.15
    mgr
    -0.15
    eyle
    -0.14
    mary
    -0.14
    imdi
    -0.14
    POSITIVE LOGITS
    655
    0.15
    Compat
    0.15
    idl
    0.15
    endance
    0.15
     Kash
    0.15
    elps
    0.14
    erno
    0.14
    vis
    0.14
    ets
    0.14
    å½ĵ
    0.14
    Activations Density 0.021%

    No Known Activations