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

    Neuronpedia

    APICircuit 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. 6-LLAMASCOPE-RES-32K
    6. 21727
    Prev
    Next
    INDEX
    Explanations

    terms related to platinum and its chemical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otten
    -0.16
    lied
    -0.15
    fst
    -0.15
    cott
    -0.15
     dil
    -0.15
    rine
    -0.15
    mse
    -0.15
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.14
    erli
    -0.14
     Heritage
    -0.14
    POSITIVE LOGITS
    isson
    0.15
    _pod
    0.15
    caf
    0.15
     withStyles
    0.14
    Duplicates
    0.14
    roker
    0.14
     Plates
    0.14
    ãĥĸãĥ«
    0.13
    asper
    0.13
    robe
    0.13
    Activations Density 0.021%

    No Known Activations