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. 24-LLAMASCOPE-RES-32K
    6. 19197
    Prev
    Next
    INDEX
    Explanations

    references to the theater and notable playwrights

    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
    alte
    -0.17
    á»į
    -0.16
    elve
    -0.14
    ÑĢеменно
    -0.14
    umd
    -0.13
     Exhib
    -0.13
    rysler
    -0.13
     Tick
    -0.13
    _ioctl
    -0.13
    acs
    -0.13
    POSITIVE LOGITS
     mask
    0.19
     masks
    0.18
    -company
    0.18
     Actors
    0.18
     company
    0.17
     Odin
    0.16
     Company
    0.16
    mask
    0.16
     Mime
    0.16
     Ensemble
    0.16
    Activations Density 0.051%

    No Known Activations