© 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. 22-LLAMASCOPE-RES-32K
    11. 16685
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to the concept of going or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uben
    -0.16
    ubits
    -0.16
    nem
    -0.15
    ÃŃnÄĽ
    -0.15
    åĭ
    -0.15
    grese
    -0.14
    inded
    -0.14
    wil
    -0.14
    inosaur
    -0.14
    Deferred
    -0.14
    POSITIVE LOGITS
     near
    0.25
     anywhere
    0.24
     gentle
    0.21
     Near
    0.20
    near
    0.19
    Near
    0.18
    adin
    0.17
     touch
    0.17
     anymore
    0.17
    Anywhere
    0.16
    Activations Density 0.036%

    No Known Activations