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. 16588
    Prev
    Next
    INDEX
    Explanations

    phrases related to combining or blending elements together

    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
    iece
    -0.16
    ÑĥÑģк
    -0.15
    "go
    -0.15
    upo
    -0.14
    acades
    -0.14
    Ñĥж
    -0.14
    zin
    -0.13
    иÑĤоÑĢ
    -0.13
    ipe
    -0.13
    orable
    -0.13
    POSITIVE LOGITS
    tures
    0.33
    TURE
    0.18
    mix
    0.17
    emean
    0.17
     mix
    0.17
    plorer
    0.16
     combination
    0.15
    .mix
    0.15
    ovnÃŃ
    0.15
    ibility
    0.15
    Activations Density 0.053%

    No Known Activations