© 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. 14712
    Prev
    Next
    INDEX
    Explanations

    references to education and scholarly institutions

    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
     alerts
    -0.14
     alert
    -0.14
    ohn
    -0.14
    oÄŁunluk
    -0.14
    chw
    -0.13
    cket
    -0.13
    oust
    -0.13
    iste
    -0.13
    ployment
    -0.13
    fred
    -0.13
    POSITIVE LOGITS
     conserv
    0.29
     Conserv
    0.28
     academy
    0.28
     Academy
    0.26
     institute
    0.26
     college
    0.26
     College
    0.24
     Poly
    0.24
     boarding
    0.23
     poly
    0.23
    Activations Density 0.170%

    No Known Activations