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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-LLAMASCOPE-RES-32K
    6. 30822
    Prev
    Next
    INDEX
    Explanations

    references to average or typical values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itional
    -0.15
    ud
    -0.14
    serie
    -0.14
    ucer
    -0.14
    ital
    -0.14
    ĢìĿ´
    -0.14
    etime
    -0.14
    uff
    -0.14
    elig
    -0.14
    ivy
    -0.14
    POSITIVE LOGITS
    flater
    0.15
    ktop
    0.15
     joe
    0.14
    hurst
    0.14
     sac
    0.14
    	Copyright
    0.14
    steen
    0.14
    preci
    0.14
    unsubscribe
    0.14
     Ear
    0.13
    Activations Density 0.020%

    No Known Activations