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. 18-LLAMASCOPE-RES-32K
    6. 28331
    Prev
    Next
    INDEX
    Explanations

    references to various community and volunteer activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yre
    -0.16
    inski
    -0.15
    à¹Ģà¸Ńà¸ĩ
    -0.15
    ÏĮÏģ
    -0.14
    okus
    -0.14
    instead
    -0.14
    zung
    -0.13
    .localized
    -0.13
    elden
    -0.13
    appen
    -0.13
    POSITIVE LOGITS
     either
    0.41
     somewhere
    0.41
     somew
    0.37
     varying
    0.34
     irgend
    0.31
     atleast
    0.31
     algún
    0.31
    either
    0.30
     Either
    0.30
    Either
    0.30
    Activations Density 0.259%

    No Known Activations