© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 20828
    Prev
    Next
    INDEX
    Explanations

    references to environmental hazards associated with oil spills and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quarry
    -0.16
    erras
    -0.15
     recipro
    -0.14
    cken
    -0.14
     Battlefield
    -0.14
    IRR
    -0.13
    é¾
    -0.13
    jang
    -0.13
     Irr
    -0.13
    idf
    -0.13
    POSITIVE LOGITS
     oil
    0.36
     Oil
    0.32
     BP
    0.30
    Oil
    0.30
     oily
    0.29
    oil
    0.28
     spill
    0.27
    BP
    0.26
     spills
    0.26
     Exxon
    0.25
    Activations Density 0.032%

    No Known Activations