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. 4-LLAMASCOPE-RES-32K
    6. 30955
    Prev
    Next
    INDEX
    Explanations

    terms related to the business sector and its interactions with the community

    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
    chwitz
    -0.17
    eniable
    -0.16
    uky
    -0.15
    ÑģÑĤа
    -0.15
    uffs
    -0.14
    ?}",
    -0.14
    samp
    -0.14
    nbsp
    -0.14
    utral
    -0.14
    ÙĪÙĬت
    -0.14
    POSITIVE LOGITS
    shan
    0.17
    pson
    0.16
    806
    0.15
    WN
    0.15
     doub
    0.15
    hoff
    0.15
     nou
    0.14
     segreg
    0.14
     toler
    0.14
    (
    0.14
    Activations Density 0.289%

    No Known Activations