© 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. 31-LLAMASCOPE-RES-32K
    11. 10391
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and the justification of claims or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eson
    -0.12
    udget
    -0.12
    ylland
    -0.12
    _optional
    -0.12
    =#
    -0.12
    ॰
    -0.12
    ismatch
    -0.11
    èī²
    -0.11
    rowsable
    -0.11
    .LogWarning
    -0.11
    POSITIVE LOGITS
     definit
    0.52
     definitive
    0.49
     definite
    0.48
     conclus
    0.46
     unequiv
    0.44
     conclusive
    0.41
     definitely
    0.40
     firm
    0.38
     certainty
    0.37
     decis
    0.35
    Activations Density 0.455%

    No Known Activations