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. 6-LLAMASCOPE-RES-32K
    6. 21508
    Prev
    Next
    INDEX
    Explanations

    terms related to facial and jaw surgery or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undra
    -0.18
    appen
    -0.17
    ppv
    -0.17
    celik
    -0.15
    icine
    -0.15
    bac
    -0.15
    Ïģιο
    -0.15
    ACCESS
    -0.15
    otas
    -0.15
    obar
    -0.14
    POSITIVE LOGITS
    h
    0.15
     Chambers
    0.14
    nu
    0.14
     Opposition
    0.14
    .MEDIA
    0.14
    bone
    0.14
     Wage
    0.14
    789
    0.14
     bone
    0.14
     Citizens
    0.13
    Activations Density 0.006%

    No Known Activations