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. 10-LLAMASCOPE-RES-32K
    6. 9414
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and names associated with significant events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ì¢Į
    -0.15
    ãĥĭãĥĥãĤ¯
    -0.14
    gorith
    -0.14
    òng
    -0.13
    crow
    -0.13
     Weiner
    -0.13
     Rect
    -0.13
    owns
    -0.13
    nell
    -0.13
     zaw
    -0.13
    POSITIVE LOGITS
     Ones
    0.17
     ones
    0.17
    egg
    0.15
    ErrorException
    0.15
    lingen
    0.14
    lien
    0.14
     Dra
    0.14
     pione
    0.14
    ActivityIndicatorView
    0.14
    utzer
    0.13
    Activations Density 0.186%

    No Known Activations