© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 18574
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to game strategy and player dynamics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     woman
    -0.19
     benchmarks
    -0.18
    à¸ķร
    -0.17
    Woman
    -0.17
     Woman
    -0.17
    woman
    -0.16
    CADE
    -0.16
     Bench
    -0.16
    STACK
    -0.16
    aggable
    -0.15
    POSITIVE LOGITS
     ball
    0.66
    ball
    0.57
    -ball
    0.54
     Ball
    0.52
    Ball
    0.50
    _ball
    0.49
     balls
    0.48
     BALL
    0.47
    .ball
    0.47
    çIJĥ
    0.46
    Activations Density 0.113%

    No Known Activations