© 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. 23-LLAMASCOPE-RES-32K
    11. 12738
    Prev
    Next
    INDEX
    Explanations

    references to groups and teams engaged in collaborative efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ening
    -0.18
    üh
    -0.18
    let
    -0.17
    tee
    -0.16
    iac
    -0.15
    ighet
    -0.15
    led
    -0.15
    ias
    -0.15
    rix
    -0.15
    ikers
    -0.15
    POSITIVE LOGITS
    geist
    0.16
     Fortress
    0.16
    -Based
    0.16
    PointSize
    0.15
     Aydın
    0.15
    empo
    0.15
    :relative
    0.15
    íļ¨
    0.15
    ategor
    0.15
    اØŃ
    0.15
    Activations Density 0.058%

    No Known Activations