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. 1-LLAMASCOPE-RES-32K
    6. 15737
    Prev
    Next
    INDEX
    Explanations

    words related to gum health and dental care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucha
    -0.16
     groupBox
    -0.14
     Bra
    -0.14
    ernel
    -0.14
    beg
    -0.13
    ough
    -0.13
    vil
    -0.13
    aná
    -0.13
    veh
    -0.13
    PED
    -0.13
    POSITIVE LOGITS
    eneg
    0.17
    elsen
    0.16
    idis
    0.15
    verity
    0.14
    .micro
    0.14
    elif
    0.14
    abet
    0.14
    soever
    0.14
    à¥ģश
    0.14
    idd
    0.14
    Activations Density 0.010%

    No Known Activations