© 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. 17-LLAMASCOPE-RES-32K
    6. 5409
    Prev
    Next
    INDEX
    Explanations

    multiple repeated phrases or punctuation in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģįãģŁ
    -0.18
    /or
    -0.17
    dera
    -0.14
    ago
    -0.14
    ily
    -0.14
    ÃŃs
    -0.13
    STR
    -0.13
    ilis
    -0.13
    spacer
    -0.13
    ocate
    -0.13
    POSITIVE LOGITS
    ÂĿ
    0.35
    ed
    0.21
    ÛĮ
    0.20
    i
    0.18
    nbsp
    0.18
    ãĢģ“
    0.17
    alama
    0.16
    ť
    0.16
    -'
    0.16
    -than
    0.15
    Activations Density 0.082%

    No Known Activations