© 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. 2-LLAMASCOPE-RES-32K
    11. 27630
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "IP" and its variations, likely related to "intellectual property" or "internet protocol."

    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
    alg
    -0.16
    icken
    -0.16
    erk
    -0.15
    ล
    -0.15
     Mock
    -0.15
     Netz
    -0.14
    itto
    -0.14
     Hancock
    -0.14
    ossa
    -0.14
    nels
    -0.14
    POSITIVE LOGITS
    pped
    0.15
    son
    0.14
    avou
    0.14
    ãĤ¡
    0.14
    UTTON
    0.14
    osemite
    0.14
    sec
    0.14
    teki
    0.14
    ÑĤик
    0.14
    uju
    0.14
    Activations Density 0.033%

    No Known Activations