© 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. 27-LLAMASCOPE-RES-32K
    11. 281
    Prev
    Next
    INDEX
    Explanations

    expressions related to formal recognition or inclusion in a group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deaux
    -0.16
    UpdateTime
    -0.12
    eler
    -0.12
     Exiting
    -0.11
    _expiry
    -0.11
    ">ÃĹ</
    -0.11
    assertCount
    -0.11
    airo
    -0.11
    Exiting
    -0.11
    expiry
    -0.10
    POSITIVE LOGITS
     start
    1.06
     starts
    1.05
     starting
    0.96
    -start
    0.94
    start
    0.92
    å¼Ģå§ĭ
    0.91
     begin
    0.91
     started
    0.90
     START
    0.89
     Starts
    0.88
    Activations Density 1.499%

    No Known Activations