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. 32397
    Prev
    Next
    INDEX
    Explanations

    references to interaction between individuals

    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
    ilarity
    -0.15
    urm
    -0.15
    lac
    -0.14
    dere
    -0.14
     Bris
    -0.14
    ega
    -0.14
    Ậ
    -0.13
    pill
    -0.13
    oden
    -0.13
    trap
    -0.13
    POSITIVE LOGITS
     other
    0.49
    other
    0.47
     Other
    0.39
    Other
    0.39
    _other
    0.36
    (other
    0.35
     autres
    0.35
     OTHER
    0.35
    åħ¶ä»ĸ
    0.34
    .other
    0.33
    Activations Density 0.017%

    No Known Activations