© 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. 24-LLAMASCOPE-RES-32K
    11. 19419
    Prev
    Next
    INDEX
    Explanations

    the word "Perhaps" as an indicator of speculation or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isoft
    -0.17
    omer
    -0.15
    assa
    -0.15
    licer
    -0.15
    ujemy
    -0.15
    arna
    -0.15
    rane
    -0.14
    rone
    -0.14
    _unsigned
    -0.14
    owi
    -0.14
    POSITIVE LOGITS
     even
    0.19
     someday
    0.18
     slightly
    0.18
     because
    0.18
     not
    0.17
    -times
    0.16
     some
    0.16
     Äijây
    0.15
     none
    0.15
     more
    0.15
    Activations Density 0.036%

    No Known Activations