© 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. 28-LLAMASCOPE-RES-32K
    11. 29679
    Prev
    Next
    INDEX
    Explanations

    terms related to "neo" and "meta" concepts, as well as related categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ombo
    -0.18
    bens
    -0.17
    gun
    -0.16
    èĢħ
    -0.16
    pu
    -0.16
    makers
    -0.16
    pcodes
    -0.15
    mente
    -0.15
    sto
    -0.15
    fully
    -0.15
    POSITIVE LOGITS
    active
    0.22
    grade
    0.18
    actively
    0.17
    cons
    0.17
     bekl
    0.16
    ener
    0.16
    ÂŃn
    0.16
    ingu
    0.15
    verted
    0.15
    future
    0.15
    Activations Density 0.042%

    No Known Activations