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. 30-LLAMASCOPE-RES-32K
    6. 4556
    Prev
    Next
    INDEX
    Explanations

    specific cricket-related statistics and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avra
    -0.17
    emet
    -0.15
     sax
    -0.15
    mps
    -0.15
    á»ī
    -0.14
    _FATAL
    -0.14
    TEE
    -0.14
    AGR
    -0.14
    æĴ
    -0.14
    inas
    -0.14
    POSITIVE LOGITS
     ATK
    0.25
     Moh
    0.24
     Manip
    0.22
     AI
    0.21
     IS
    0.20
    IS
    0.20
     Hero
    0.20
    AI
    0.20
     East
    0.19
     Mohammed
    0.19
    Activations Density 0.003%

    No Known Activations