© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 24250
    Prev
    Next
    INDEX
    Explanations

    sentences that contain guidance or instructions regarding planning and organizing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĤãģ£ãģ¨
    -0.17
    orthand
    -0.15
    òi
    -0.14
    го
    -0.14
    coverage
    -0.14
    orce
    -0.14
    umpy
    -0.14
    ाहन
    -0.14
    abeth
    -0.14
    crest
    -0.14
    POSITIVE LOGITS
     majority
    0.16
    odia
    0.16
    as
    0.14
     shifting
    0.14
    lass
    0.14
     Antony
    0.14
    idar
    0.13
    sole
    0.13
    bes
    0.13
     therefore
    0.13
    Activations Density 0.385%

    No Known Activations