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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 14045
    Prev
    Next
    INDEX
    Explanations

    descriptive terms for clothing and fashion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    810
    -0.15
    rippling
    -0.14
    çıł
    -0.14
    ixe
    -0.14
     toes
    -0.13
    èĦĤ
    -0.13
    endas
    -0.13
    rine
    -0.13
    alim
    -0.13
    oken
    -0.13
    POSITIVE LOGITS
     pul
    0.33
     jumper
    0.30
     shirt
    0.29
     vest
    0.29
     jacket
    0.27
     jumps
    0.27
     sweater
    0.27
     dress
    0.25
     crop
    0.25
     cardi
    0.24
    Activations Density 0.178%

    No Known Activations