© 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. 17130
    Prev
    Next
    INDEX
    Explanations

    references to historical artifacts and heritage sites

    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
     Doll
    -0.14
    \Active
    -0.14
    abelle
    -0.14
     Styled
    -0.13
     gravel
    -0.13
     Sculpt
    -0.13
    inho
    -0.13
    063
    -0.13
    едак
    -0.13
     Wire
    -0.13
    POSITIVE LOGITS
     fres
    0.49
     Fres
    0.35
     mur
    0.30
     ceiling
    0.29
     mural
    0.26
     wall
    0.26
     fri
    0.25
     Ceiling
    0.25
    å£ģ
    0.24
     scenes
    0.24
    Activations Density 0.093%

    No Known Activations