© 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. 2-LLAMASCOPE-RES-32K
    11. 16472
    Prev
    Next
    INDEX
    Explanations

    references to aquatic environments and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apult
    -0.14
    edom
    -0.14
    ocs
    -0.14
    alogy
    -0.13
    CLUS
    -0.13
    teki
    -0.13
    ndef
    -0.13
    787
    -0.13
    apping
    -0.13
     Ui
    -0.13
    POSITIVE LOGITS
    .omg
    0.17
     Kod
    0.17
    jian
    0.15
     saturn
    0.15
     代
    0.15
    739
    0.15
     deep
    0.14
    qml
    0.14
    iment
    0.14
    alla
    0.14
    Activations Density 0.043%

    No Known Activations