© 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. 12388
    Prev
    Next
    INDEX
    Explanations

    references to evidence and documentation in the context of claims and insurance

    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
    ynos
    -0.14
     lif
    -0.14
    olean
    -0.14
    oki
    -0.14
    926
    -0.14
     ön
    -0.14
    HING
    -0.13
     disclosures
    -0.13
    OrUpdate
    -0.13
     اط
    -0.13
    POSITIVE LOGITS
     record
    0.31
     records
    0.29
    record
    0.28
    records
    0.27
     Record
    0.27
    Record
    0.25
     RECORD
    0.25
     Records
    0.25
    Records
    0.24
     documentation
    0.23
    Activations Density 0.062%

    No Known Activations