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. 11823
    Prev
    Next
    INDEX
    Explanations

    words related to processes of change and transformation

    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
    ÑĥÑĢн
    -0.17
    _EMIT
    -0.16
     deduct
    -0.16
    _triggered
    -0.16
    'gc
    -0.15
    åΰäºĨ
    -0.15
    aunch
    -0.15
     Embed
    -0.15
    eselect
    -0.15
     compens
    -0.14
    POSITIVE LOGITS
     auction
    0.17
    ushman
    0.17
     jugg
    0.17
     courier
    0.16
    arrow
    0.16
     butcher
    0.15
     legisl
    0.15
     debug
    0.15
     lain
    0.15
     pawn
    0.15
    Activations Density 1.010%

    No Known Activations