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. 13-LLAMASCOPE-RES-32K
    6. 16552
    Prev
    Next
    INDEX
    Explanations

    financial terms and figures related to stock ownership and investment activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oller
    -0.19
     Cri
    -0.17
    iling
    -0.15
    Offsets
    -0.15
    mong
    -0.15
    agine
    -0.15
    Pawn
    -0.15
    елик
    -0.15
    iks
    -0.14
    erals
    -0.14
    POSITIVE LOGITS
     Ryder
    0.17
    )did
    0.16
    浦
    0.15
     TRADE
    0.14
     AHL
    0.14
    izon
    0.13
     phân
    0.13
     Scalars
    0.13
     büy
    0.13
     Javier
    0.13
    Activations Density 0.008%

    No Known Activations