© 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. 25-LLAMASCOPE-RES-32K
    11. 18337
    Prev
    Next
    INDEX
    Explanations

    details about jewelry, specifically rings and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    串
    -0.17
     Hanging
    -0.16
     neck
    -0.16
     necklace
    -0.16
    ipo
    -0.15
     hanging
    -0.15
    acas
    -0.15
    ÑĢаÑģ
    -0.15
    -neck
    -0.15
     Necklace
    -0.15
    POSITIVE LOGITS
     ring
    0.36
     Ring
    0.30
     engagement
    0.29
     rings
    0.28
     Engagement
    0.28
    -ring
    0.27
    Ring
    0.27
     band
    0.26
    ring
    0.23
     Band
    0.23
    Activations Density 0.025%

    No Known Activations