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. 23891
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "some" in various contexts

    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
    irie
    -0.15
    ped
    -0.15
    umer
    -0.15
    tempt
    -0.14
    uet
    -0.14
    hec
    -0.14
    ned
    -0.14
    ÑĤÑĢи
    -0.14
    çļĦä¸Ģ个
    -0.13
    ed
    -0.13
    POSITIVE LOGITS
    /all
    0.25
    place
    0.24
    许
    0.19
    룬
    0.18
    kind
    0.18
    -times
    0.18
    ones
    0.17
    akin
    0.17
    æł·çļĦ
    0.17
    hw
    0.17
    Activations Density 0.097%

    No Known Activations