© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 1733
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to equipment and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EventHandler
    -0.14
    #+
    -0.14
    ,:
    -0.13
     Stout
    -0.13
    ORM
    -0.13
     Ø·ÛĮ
    -0.13
    æĶ
    -0.12
    defs
    -0.12
     ãĥĬ
    -0.12
    inger
    -0.12
    POSITIVE LOGITS
     your
    0.51
    ä½łçļĦ
    0.44
    your
    0.40
     our
    0.40
     ваÑĪ
    0.39
    æĤ¨çļĦ
    0.38
     his
    0.36
     Your
    0.33
     seu
    0.32
     my
    0.32
    Activations Density 0.517%

    No Known Activations