© 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. 26-LLAMASCOPE-RES-32K
    11. 11864
    Prev
    Next
    INDEX
    Explanations

    references to research committees, reviews, and evaluations related to academic or organizational oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anken
    -0.15
     Pazar
    -0.15
     supervised
    -0.14
    RuntimeObject
    -0.14
    ÑģÑĤвенное
    -0.14
    æĵį
    -0.14
    ĽĪ
    -0.14
    .Bunifu
    -0.14
    eç
    -0.14
    orno
    -0.13
    POSITIVE LOGITS
     committee
    0.52
     Working
    0.47
     working
    0.46
     task
    0.46
     Task
    0.44
    Working
    0.43
     Committee
    0.41
    working
    0.41
     committees
    0.39
    committee
    0.39
    Activations Density 0.261%

    No Known Activations