© 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. 30-LLAMASCOPE-RES-32K
    11. 11619
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific references related to notable individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /Dk
    -0.16
    eya
    -0.15
    imat
    -0.15
    -UA
    -0.14
    Cookie
    -0.14
    ChildIndex
    -0.14
    ½æķ°
    -0.14
     Shelf
    -0.14
    cot
    -0.14
    Diagnostic
    -0.14
    POSITIVE LOGITS
    azz
    0.17
    utable
    0.16
     Surg
    0.15
    /general
    0.15
    wi
    0.15
    hurst
    0.14
    ylko
    0.14
    ebo
    0.14
    elay
    0.14
    abler
    0.14
    Activations Density 0.017%

    No Known Activations