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. 26525
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional situations and possibilities

    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
    .dk
    -0.18
    arel
    -0.15
    ropri
    -0.15
    ello
    -0.14
    ebin
    -0.14
    arella
    -0.14
    atta
    -0.14
    steen
    -0.14
    heimer
    -0.14
    adesh
    -0.13
    POSITIVE LOGITS
    thr
    0.14
     kept
    0.14
    _keep
    0.14
    aph
    0.14
    /un
    0.13
    cen
    0.13
    ãĥ©ãĤ¹
    0.13
    fen
    0.13
    unt
    0.13
    790
    0.13
    Activations Density 0.028%

    No Known Activations