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. 28409
    Prev
    Next
    INDEX
    Explanations

    references to specific animal and plant species

    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
    rud
    -0.15
    acock
    -0.14
    alex
    -0.14
     Alexand
    -0.14
     FUNC
    -0.14
    arus
    -0.14
    ÏĢα
    -0.14
    vet
    -0.14
     Sink
    -0.14
    quir
    -0.13
    POSITIVE LOGITS
     found
    0.21
    found
    0.20
    Found
    0.19
     Found
    0.18
     widespread
    0.17
     natives
    0.17
     native
    0.17
     encontr
    0.16
    à¸ŀà¸ļ
    0.16
    IME
    0.15
    Activations Density 0.095%

    No Known Activations