© 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. 31-LLAMASCOPE-RES-32K
    11. 10916
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "ex" in various contexts, often related to actions or conditions of removal or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynn
    -0.17
    excel
    -0.15
    .Sdk
    -0.14
    .Automation
    -0.14
    ElementType
    -0.14
    lla
    -0.14
    bz
    -0.14
    ottle
    -0.14
    annah
    -0.14
    iveau
    -0.14
    POSITIVE LOGITS
    propri
    0.30
    oner
    0.29
    hort
    0.28
    acerb
    0.27
    communic
    0.26
    communication
    0.25
    hum
    0.25
    cul
    0.24
    orc
    0.24
    erc
    0.24
    Activations Density 0.014%

    No Known Activations