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. 19-LLAMASCOPE-RES-32K
    6. 25921
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works

    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
    ascar
    -0.18
    ossa
    -0.17
     Pear
    -0.16
    vel
    -0.16
    aná
    -0.14
    iaux
    -0.14
    *=*=
    -0.14
    abay
    -0.14
    uled
    -0.14
    以
    -0.14
    POSITIVE LOGITS
    â΍
    0.18
     --
    0.18
    é¡ŀ
    0.16
    âĢį
    0.16
     âΧ
    0.16
     unp
    0.16
     hoop
    0.15
     İli
    0.14
    /admin
    0.14
    inux
    0.14
    Activations Density 0.076%

    No Known Activations