© 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. 4-LLAMASCOPE-RES-32K
    11. 3986
    Prev
    Next
    INDEX
    Explanations

    references to films and cinematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andin
    -0.16
    amik
    -0.15
    sei
    -0.15
    ãĥ¼ãĤ¹
    -0.15
    ustr
    -0.14
    iona
    -0.14
     cover
    -0.14
    ient
    -0.14
    eterminate
    -0.13
     warped
    -0.13
    POSITIVE LOGITS
    inalg
    0.18
    stants
    0.17
    PropTypes
    0.15
    elmet
    0.15
    adium
    0.14
     hydr
    0.14
    .LENGTH
    0.13
    aspers
    0.13
    etten
    0.13
     slope
    0.13
    Activations Density 0.045%

    No Known Activations