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. 29-LLAMASCOPE-RES-32K
    6. 17380
    Prev
    Next
    INDEX
    Explanations

    mentions of specific comedy performances and festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alsa
    -0.15
    acomment
    -0.15
     Symphony
    -0.14
    anten
    -0.14
     æİ
    -0.14
    inen
    -0.14
    lhs
    -0.14
     luder
    -0.14
    :async
    -0.14
    Gatt
    -0.14
    POSITIVE LOGITS
     Fr
    0.35
     Edinburgh
    0.34
    FRING
    0.29
     fringe
    0.28
     comedy
    0.25
    fr
    0.24
    edin
    0.23
     cab
    0.22
    Fr
    0.22
     previews
    0.22
    Activations Density 0.005%

    No Known Activations