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. 20814
    Prev
    Next
    INDEX
    Explanations

    terms related to service providers and cloud computing offerings

    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
    ijkstra
    -0.17
    -rating
    -0.14
    à¥įà¤Łà¤®
    -0.14
    ÛĮÛĮÙĨ
    -0.14
    ÑĢиÑģ
    -0.14
     Raised
    -0.14
    aku
    -0.13
    IRE
    -0.13
    leck
    -0.13
    icker
    -0.13
    POSITIVE LOGITS
    osaur
    0.16
    ocale
    0.15
    eut
    0.15
     Replay
    0.14
    aub
    0.14
    ãĤ·ãĥ§
    0.14
    pecting
    0.14
    hots
    0.14
    ackBar
    0.13
    .prot
    0.13
    Activations Density 0.114%

    No Known Activations