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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21270
    Prev
    Next
    INDEX
    Explanations

    terms related to animal diseases and their impacts

    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
    ãĥ¼ãĥł
    -0.15
    FFFF
    -0.15
    HexString
    -0.14
    esktop
    -0.14
    ναÏĤ
    -0.14
     overhead
    -0.14
    .insertBefore
    -0.14
     ìĭ¸
    -0.13
    аÑĢа
    -0.13
    nen
    -0.13
    POSITIVE LOGITS
     stabilization
    0.15
     stabil
    0.15
    /link
    0.14
     ;č↵
    0.14
    ahir
    0.14
    ingleton
    0.13
    بÙĦ
    0.13
     Assurance
    0.13
     fort
    0.13
     NIL
    0.13
    Activations Density 0.012%

    No Known Activations