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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 25060
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "called out" and its variations as well as expressions indicating communication or addressing someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.18
    chyb
    -0.15
    aylight
    -0.15
    ftime
    -0.15
    æ³ķ人
    -0.15
    .SDK
    -0.14
    reur
    -0.14
    mani
    -0.14
    eature
    -0.14
    mey
    -0.14
    POSITIVE LOGITS
    ragen
    0.17
     Richt
    0.16
    zee
    0.15
    oo
    0.15
     tam
    0.14
    ales
    0.14
    Ïģά
    0.14
    ãĥ¼ãĥģ
    0.14
    83
    0.14
    tern
    0.14
    Activations Density 0.158%

    No Known Activations