Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-LLAMASCOPE-RES-32K
    6. 11852
    Prev
    Next
    INDEX
    Explanations

    references to future trends and innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sg
    -0.18
    ierz
    -0.16
    лÑĮ
    -0.16
    sst
    -0.16
    oldemort
    -0.15
    itches
    -0.15
     bon
    -0.15
    ledged
    -0.15
    tring
    -0.14
    phan
    -0.14
    POSITIVE LOGITS
     tense
    0.21
    heads
    0.18
    <void
    0.17
     shock
    0.17
     Shock
    0.17
    amura
    0.16
    -proof
    0.16
    wei
    0.16
     æĿ
    0.15
    èŀº
    0.15
    Activations Density 0.010%

    No Known Activations