© 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. 30-LLAMASCOPE-RES-32K
    6. 11479
    Prev
    Next
    INDEX
    Explanations

    references to sailing and marine-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ship
    -0.26
     ships
    -0.24
     Ship
    -0.22
    Ship
    -0.22
     коÑĢаб
    -0.21
    _ship
    -0.21
     submarine
    -0.20
     maritime
    -0.20
     Ships
    -0.19
    ship
    -0.19
    POSITIVE LOGITS
     charter
    0.28
     chart
    0.26
     y
    0.25
     Charter
    0.23
     Rally
    0.23
     rally
    0.23
     anch
    0.21
     passages
    0.21
     Suns
    0.21
     mo
    0.21
    Activations Density 0.050%

    No Known Activations