© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-32K
    11. 5597
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing existence, conditions, and relationships

    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
    heck
    -0.15
    razy
    -0.14
    éĤ£ä¹Ī
    -0.14
    ikel
    -0.14
    oser
    -0.14
    eyn
    -0.14
    w
    -0.14
     Pip
    -0.13
    nd
    -0.13
    ues
    -0.13
    POSITIVE LOGITS
    calar
    0.23
     nÃło
    0.19
    kate
    0.16
    Wunused
    0.16
     cui
    0.15
     which
    0.15
    à¥įतव
    0.15
    branch
    0.14
    quisite
    0.14
    gene
    0.14
    Activations Density 0.126%

    No Known Activations