© 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. 18331
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" in various forms, indicating a focus on sight or observation-related actions

    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
    iom
    -0.16
    olik
    -0.15
    ollah
    -0.15
    .shiro
    -0.15
    idar
    -0.14
    150
    -0.14
    ula
    -0.14
    eker
    -0.14
    elix
    -0.14
    uada
    -0.14
    POSITIVE LOGITS
     closely
    0.21
     up
    0.20
    istrovstvÃŃ
    0.17
     at
    0.17
     carefully
    0.17
     online
    0.16
     through
    0.16
     around
    0.16
     elsewhere
    0.16
     Twice
    0.16
    Activations Density 0.049%

    No Known Activations