© 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. 23723
    Prev
    Next
    INDEX
    Explanations

    actions related to confrontation and incapacitation in high-stakes scenarios

    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
    สร
    -0.16
    assin
    -0.15
    762
    -0.15
    042
    -0.15
    oted
    -0.14
     jud
    -0.14
    å¡
    -0.14
    peare
    -0.14
    etre
    -0.14
    anza
    -0.14
    POSITIVE LOGITS
    ownt
    0.19
    kses
    0.16
    ëŀį
    0.15
    ông
    0.15
    engu
    0.15
    conti
    0.15
    exus
    0.14
    /lg
    0.14
    ochrome
    0.14
    uda
    0.14
    Activations Density 0.143%

    No Known Activations