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. 31-LLAMASCOPE-RES-32K
    6. 6820
    Prev
    Next
    INDEX
    Explanations

    references to the Marvel Cinematic Universe, specifically relating to the show "Agents of SHIELD" and its connections to the greater film narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OLEAN
    -0.18
    KI
    -0.16
    ILI
    -0.15
    SSIP
    -0.15
    icer
    -0.15
     OCI
    -0.15
    assi
    -0.15
     GPI
    -0.15
    GP
    -0.14
    unei
    -0.14
    POSITIVE LOGITS
     Ant
    0.42
     ANT
    0.34
     ants
    0.33
    Ant
    0.33
     Marvel
    0.29
     Peyton
    0.28
     Scott
    0.28
     ant
    0.28
     Rudd
    0.28
     Avengers
    0.26
    Activations Density 0.005%

    No Known Activations