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. 30-LLAMASCOPE-RES-32K
    6. 4862
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to laws and regulations

    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
    erus
    -0.16
    agon
    -0.15
    Äł
    -0.14
    hawks
    -0.14
    bia
    -0.14
     çϼ
    -0.14
    irim
    -0.13
    Denied
    -0.13
     Chall
    -0.13
    loys
    -0.13
    POSITIVE LOGITS
     states
    0.38
    states
    0.29
     sets
    0.28
     bars
    0.27
     spells
    0.26
     specifies
    0.25
     author
    0.24
    .states
    0.24
     STATES
    0.24
     Bars
    0.23
    Activations Density 0.204%

    No Known Activations