© 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. 30-LLAMASCOPE-RES-32K
    11. 17380
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" in various forms, indicating a focus on expressions of anticipation or interest

    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
    uali
    -0.18
    æĤł
    -0.16
    ooth
    -0.16
    haven
    -0.15
    otta
    -0.15
    _LEG
    -0.15
     Gol
    -0.14
    occo
    -0.14
     åħ«
    -0.14
    EMPLARY
    -0.14
    POSITIVE LOGITS
     forward
    0.46
    forward
    0.31
    -forward
    0.27
     fwd
    0.27
     FORWARD
    0.27
     forwarding
    0.27
     forwarded
    0.26
    .forward
    0.26
    _forward
    0.26
     f
    0.24
    Activations Density 0.013%

    No Known Activations