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. 32756
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and assertions in code

    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
    AWN
    -0.15
     Ment
    -0.14
    inus
    -0.14
    ontent
    -0.14
    olet
    -0.14
    .Vertex
    -0.13
    šak
    -0.13
    oru
    -0.13
    ernal
    -0.13
    ion
    -0.13
    POSITIVE LOGITS
    Ń
    0.18
    Looper
    0.16
    ANCH
    0.15
     Checking
    0.14
    å©·
    0.14
    .synthetic
    0.13
    .opendaylight
    0.13
    775
    0.13
    andle
    0.13
    Checking
    0.13
    Activations Density 0.053%

    No Known Activations