© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16299
    Prev
    Next
    INDEX
    Explanations

    speculations about wrestling events and character outcomes

    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
    ramer
    -0.17
    .mb
    -0.14
     BASIS
    -0.14
    venes
    -0.14
    aramel
    -0.14
    .AutoSizeMode
    -0.14
    _MB
    -0.14
    ldr
    -0.14
    /runtime
    -0.14
    haar
    -0.14
    POSITIVE LOGITS
     WWE
    0.36
     wrestlers
    0.36
     wrestler
    0.33
     wrestling
    0.33
     Wrestling
    0.31
     Wrest
    0.30
     wrest
    0.29
     McMahon
    0.28
     kay
    0.28
     ring
    0.28
    Activations Density 0.155%

    No Known Activations