© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 423
    Prev
    Next
    INDEX
    Explanations

    references to party supplies and events, particularly those involving balloons and outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.16
    Unhandled
    -0.14
    ãĤŃãĥ¼
    -0.14
    ouver
    -0.14
    è®
    -0.13
    esan
    -0.13
     Bone
    -0.13
    ueva
    -0.13
     bone
    -0.13
    .axis
    -0.13
    POSITIVE LOGITS
     inflation
    0.58
     inflate
    0.55
    inflate
    0.50
     inflated
    0.50
     Inflate
    0.49
     deflate
    0.48
     infl
    0.45
     balloons
    0.44
     balloon
    0.43
    .inflate
    0.40
    Activations Density 0.107%

    No Known Activations