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. 31-LLAMASCOPE-RES-32K
    6. 2117
    Prev
    Next
    INDEX
    Explanations

    themes related to artistic exploration and the creative process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .springboot
    -0.13
    .asp
    -0.13
    åIJ¹
    -0.13
     Explanation
    -0.13
    abeled
    -0.12
     blaming
    -0.12
     Personality
    -0.12
     blamed
    -0.12
     improvement
    -0.12
    xae
    -0.12
    POSITIVE LOGITS
     renegot
    0.19
    -archive
    0.19
     collage
    0.18
     referencing
    0.18
     rupt
    0.17
     destabil
    0.17
     oscill
    0.17
    Untitled
    0.17
    /install
    0.16
     activated
    0.16
    Activations Density 0.152%

    No Known Activations