© 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. 20-LLAMASCOPE-RES-32K
    11. 28667
    Prev
    Next
    INDEX
    Explanations

    negative contractions and phrases expressing doubt or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endale
    -0.16
    unker
    -0.16
    åĩ
    -0.16
     Kum
    -0.15
     Patch
    -0.14
    umeric
    -0.14
    ptime
    -0.14
     ov
    -0.14
     cv
    -0.14
     patch
    -0.14
    POSITIVE LOGITS
    bers
    0.16
     sey
    0.15
    اسÙĬ
    0.15
    chalk
    0.14
    '].$
    0.14
    ÏĦαÏĤ
    0.14
     Dün
    0.14
     Blizzard
    0.14
    lashes
    0.14
    .xmlbeans
    0.14
    Activations Density 0.036%

    No Known Activations