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. 9-LLAMASCOPE-RES-32K
    6. 2633
    Prev
    Next
    INDEX
    Explanations

    activity related to education and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ê°ģ
    -0.17
    rupa
    -0.15
    ;element
    -0.15
    imat
    -0.14
     cin
    -0.14
    ırken
    -0.14
     ITER
    -0.13
    igan
    -0.13
    glob
    -0.13
    linkplain
    -0.13
    POSITIVE LOGITS
    aux
    0.18
    asse
    0.15
     Pearce
    0.15
    021
    0.15
    325
    0.14
    &S
    0.14
    ownt
    0.14
    .ExecuteReader
    0.14
     ÑĤабли
    0.13
    олай
    0.13
    Activations Density 0.333%

    No Known Activations