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. 25102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" in various contexts

    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
    ilia
    -0.16
     ecosystem
    -0.15
    uts
    -0.15
     pent
    -0.15
     dealloc
    -0.14
     lets
    -0.14
    etry
    -0.14
     Tân
    -0.14
     Ec
    -0.14
     Jen
    -0.14
    POSITIVE LOGITS
    shit
    0.18
    encv
    0.15
    WithTag
    0.15
    ToDate
    0.15
    strup
    0.14
    NonQuery
    0.14
    esi
    0.14
    nicos
    0.14
    arp
    0.14
    /embed
    0.14
    Activations Density 0.007%

    No Known Activations