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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 12711
    Prev
    Next
    INDEX
    Explanations

    variations of the word "fix" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alu
    -0.16
    edn
    -0.15
    ilet
    -0.15
    ceased
    -0.15
    _________________↵↵
    -0.15
    veau
    -0.14
    ãĥ¼ãĥ«
    -0.14
    UNIX
    -0.14
    seys
    -0.14
     Elephant
    -0.14
    POSITIVE LOGITS
    tures
    0.32
    TURE
    0.24
    (es
    0.23
    ated
    0.20
    -it
    0.17
    uring
    0.17
    xed
    0.17
    ity
    0.16
    .fix
    0.16
    sure
    0.16
    Activations Density 0.027%

    No Known Activations