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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17879
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or seeking

    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
    eka
    -0.16
    alfa
    -0.15
     sed
    -0.15
    agal
    -0.15
    contest
    -0.15
    catch
    -0.14
    urved
    -0.14
     lá»ĩ
    -0.14
    anguage
    -0.14
     Sed
    -0.14
    POSITIVE LOGITS
    /search
    0.24
    (search
    0.22
     search
    0.22
     SEARCH
    0.21
     searching
    0.21
    =search
    0.20
    .search
    0.20
    SEARCH
    0.20
     Searching
    0.19
    (Search
    0.19
    Activations Density 0.065%

    No Known Activations