© 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. 12-LLAMASCOPE-RES-32K
    11. 31662
    Prev
    Next
    INDEX
    Explanations

    references to swimming and water-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igne
    -0.19
    à¤Łà¤ķ
    -0.15
    eve
    -0.15
     ìĤ¬íķŃ
    -0.15
    eer
    -0.15
    óc
    -0.15
    ìĤ¬íķŃ
    -0.14
    IMA
    -0.14
    reet
    -0.14
    terra
    -0.14
    POSITIVE LOGITS
     swimming
    0.21
     Swimming
    0.16
    /body
    0.16
    erb
    0.15
    erman
    0.15
    /sw
    0.15
    untu
    0.14
    isode
    0.14
     Sad
    0.14
     paddle
    0.13
    Activations Density 0.027%

    No Known Activations