© 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. 5-LLAMASCOPE-RES-32K
    11. 470
    Prev
    Next
    INDEX
    Explanations

    comparisons and reviews of video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĦ
    -0.14
    Ïīμα
    -0.14
    ndef
    -0.14
    ONO
    -0.14
    ornado
    -0.14
    itur
    -0.14
    aines
    -0.14
    tual
    -0.14
     capt
    -0.13
     ucwords
    -0.13
    POSITIVE LOGITS
    oca
    0.14
    zzo
    0.13
     OST
    0.13
    odka
    0.13
     Wax
    0.13
    UTH
    0.13
    earch
    0.13
    uese
    0.13
    oÅĽci
    0.13
    packing
    0.12
    Activations Density 0.501%

    No Known Activations