Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28404
    Prev
    Next
    INDEX
    Explanations

    expressions of ambition and expectation regarding personal and professional goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sov
    -0.16
     gross
    -0.15
    gross
    -0.15
    ancode
    -0.15
    akis
    -0.15
    alem
    -0.14
     dikke
    -0.14
    chron
    -0.14
     awaited
    -0.14
     predicted
    -0.14
    POSITIVE LOGITS
    /go
    0.28
     goals
    0.19
    Goals
    0.17
     hopes
    0.17
    ç«ĭãģ¦
    0.17
     Goals
    0.17
    goals
    0.16
     doÄŁrult
    0.16
     ambitions
    0.15
    ILLA
    0.15
    Activations Density 0.092%

    No Known Activations