© 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. 26467
    Prev
    Next
    INDEX
    Explanations

    U.S. state names and their abbreviations

    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
    arine
    -0.16
    adius
    -0.15
    ç¦
    -0.15
    arte
    -0.15
    orre
    -0.15
    !
    -0.14
    fang
    -0.14
    inator
    -0.14
    ér
    -0.14
     decision
    -0.14
    POSITIVE LOGITS
     konkrét
    0.15
     seedu
    0.15
    ETCH
    0.14
    laughter
    0.14
    leck
    0.14
    escal
    0.14
     Snowden
    0.14
     omas
    0.14
    (strtolower
    0.14
    :UITableView
    0.14
    Activations Density 0.057%

    No Known Activations