Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32502
    Prev
    Next
    INDEX
    Explanations

    phrases related to access to essential services and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucas
    -0.20
    ellas
    -0.17
     Chains
    -0.15
    haar
    -0.15
    aru
    -0.15
    iras
    -0.15
     chains
    -0.14
    ayah
    -0.14
     chain
    -0.14
     Willis
    -0.14
    POSITIVE LOGITS
    -runtime
    0.15
    hed
    0.15
    amu
    0.15
    jej
    0.14
    ged
    0.14
    ixon
    0.14
    idor
    0.14
    ona
    0.14
    çĴ
    0.14
    posit
    0.14
    Activations Density 0.079%

    No Known Activations