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. 21650
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding victimization and marginalization of individuals or groups

    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
    alle
    -0.15
    rics
    -0.15
    CCA
    -0.14
    illery
    -0.14
    Affected
    -0.14
    YLE
    -0.13
    é«ĺæ¸ħ
    -0.13
    pls
    -0.13
    emean
    -0.13
     adopt
    -0.13
    POSITIVE LOGITS
    ForObject
    0.15
    .Html
    0.15
    Aspect
    0.14
    ÑĢом
    0.14
    chwitz
    0.14
    imore
    0.14
    íĥĢìĿ´
    0.14
    bios
    0.14
    -Allow
    0.14
    å±
    0.14
    Activations Density 0.246%

    No Known Activations