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. 11-LLAMASCOPE-RES-32K
    6. 29182
    Prev
    Next
    INDEX
    Explanations

    the phrase "leave a comment"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bum
    -0.17
    ramento
    -0.16
    calar
    -0.15
    ÃŃl
    -0.15
    tual
    -0.15
    raci
    -0.14
    idon
    -0.14
    uario
    -0.14
    ovice
    -0.14
    QUIRE
    -0.14
    POSITIVE LOGITS
    urg
    0.15
     resc
    0.14
    @s
    0.14
    ollar
    0.14
    ood
    0.14
    çłĶç©¶æīĢ
    0.14
    BuilderFactory
    0.14
    .tw
    0.13
    opard
    0.13
    .master
    0.13
    Activations Density 0.009%

    No Known Activations