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. 18-LLAMASCOPE-RES-32K
    6. 6221
    Prev
    Next
    INDEX
    Explanations

    references to surfaces 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 @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ü
    -0.17
    lio
    -0.16
    lia
    -0.16
    Ùħ
    -0.15
    ish
    -0.15
    ew
    -0.15
    nap
    -0.15
    apse
    -0.15
    la
    -0.14
    nes
    -0.14
    POSITIVE LOGITS
    /interface
    0.22
    -mounted
    0.19
     tension
    0.17
    /sub
    0.17
     Pell
    0.15
    ival
    0.15
    ANDOM
    0.15
    utex
    0.15
    -level
    0.15
    osal
    0.15
    Activations Density 0.016%

    No Known Activations