© 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. 30-LLAMASCOPE-RES-32K
    11. 17350
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there," indicating a focus on the presence or existence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rix
    -0.17
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.14
    reno
    -0.14
    idak
    -0.14
    TestCategory
    -0.14
    ÑģÑĮого
    -0.14
    reck
    -0.14
    _Tis
    -0.13
     principalTable
    -0.13
    ezier
    -0.13
    POSITIVE LOGITS
     remain
    0.30
     continue
    0.28
     appear
    0.27
     remains
    0.23
     continues
    0.23
     appears
    0.21
    continue
    0.21
    appear
    0.21
     were
    0.21
     have
    0.21
    Activations Density 0.064%

    No Known Activations