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. 3-LLAMASCOPE-RES-32K
    6. 23838
    Prev
    Next
    INDEX
    Explanations

    references to "facts" in legal or evaluative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lernen
    -0.16
    avra
    -0.16
    iggs
    -0.15
    -bodied
    -0.15
    llib
    -0.15
    gL
    -0.15
    ãĤ
    -0.15
    echa
    -0.14
    scribe
    -0.14
    /cms
    -0.14
    POSITIVE LOGITS
    UY
    0.16
    <decltype
    0.15
    //{{
    0.15
    kt
    0.15
    arem
    0.15
    Ps
    0.15
    aket
    0.15
    Pocket
    0.14
    KT
    0.14
    ãĥ³ãĥĩãĤ£
    0.14
    Activations Density 0.009%

    No Known Activations