Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 2288
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "used" and related terms indicating utilization or application

    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
    ollapse
    -0.16
    olle
    -0.15
     SqlParameter
    -0.14
    onec
    -0.14
    .btnSave
    -0.14
    enting
    -0.14
    éĺª
    -0.14
    uxe
    -0.14
    dej
    -0.14
    isci
    -0.14
    POSITIVE LOGITS
    ाà¤Ī
    0.15
    tlement
    0.15
    803
    0.14
    اÛĮØ´
    0.13
     SH
    0.13
    edn
    0.13
    vor
    0.13
    656
    0.13
    .ActionListener
    0.13
    aker
    0.12
    Activations Density 0.089%

    No Known Activations