© 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. 23070
    Prev
    Next
    INDEX
    Explanations

    references to effort and acknowledgment of hard work

    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
    ز
    -0.14
    Å¡Å¥
    -0.13
    ResultSet
    -0.13
    okud
    -0.13
    759
    -0.13
    ista
    -0.13
    aldi
    -0.13
    /window
    -0.13
     Hicks
    -0.13
    onda
    -0.13
    POSITIVE LOGITS
     effort
    0.56
     hard
    0.49
     labour
    0.40
     efforts
    0.40
    åĬªåĬĽ
    0.39
     work
    0.39
    hard
    0.38
     labor
    0.37
    è¾Ľ
    0.35
     sweat
    0.34
    Activations Density 0.507%

    No Known Activations