© 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. 18365
    Prev
    Next
    INDEX
    Explanations

    negations and refusals in the text

    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
    nty
    -0.15
    ãĤ¸ãĤ¢
    -0.15
    ntag
    -0.14
    omy
    -0.14
    afort
    -0.13
    OVE
    -0.13
    اÛĮØ´
    -0.13
    awns
    -0.12
    ='".
    -0.12
    롯
    -0.12
    POSITIVE LOGITS
     necessarily
    0.41
     mind
    0.34
     ever
    0.32
     even
    0.31
     exactly
    0.29
     dare
    0.27
     necessary
    0.26
     EVER
    0.25
     bother
    0.25
     anymore
    0.25
    Activations Density 0.170%

    No Known Activations