© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 850
    Prev
    Next
    INDEX
    Explanations

    the word "like" as a connector or filler phrase

    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
    tainment
    -0.16
    ignon
    -0.15
    ayout
    -0.15
    ubar
    -0.15
    hiba
    -0.14
     nackte
    -0.14
    pedo
    -0.14
    .UnitTesting
    -0.14
    è®®
    -0.14
    bilt
    -0.14
    POSITIVE LOGITS
     never
    0.16
    MBProgressHUD
    0.15
     wildfire
    0.14
    -minded
    0.14
     ours
    0.14
     Never
    0.14
    RIA
    0.14
    unset
    0.13
     nhau
    0.13
    ht
    0.13
    Activations Density 0.042%

    No Known Activations