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. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32467
    Prev
    Next
    INDEX
    Explanations

    terms related to smear campaigns and their impacts on individuals in politics

    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
    getDisplay
    -0.15
    ulu
    -0.15
    ono
    -0.14
    unda
    -0.14
    ewolf
    -0.14
    egin
    -0.14
    å´İ
    -0.14
    κÎŃ
    -0.14
    çīĩ
    -0.13
     Gew
    -0.13
    POSITIVE LOGITS
     dirt
    0.35
     Dirt
    0.33
     opp
    0.25
     dirty
    0.24
    _dirty
    0.22
     smear
    0.21
     negative
    0.20
     mud
    0.19
    negative
    0.19
    dirty
    0.19
    Activations Density 0.411%

    No Known Activations