© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 15247
    Prev
    Next
    INDEX
    Explanations

    mentions of ethical concerns and practices related to animal-derived products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earrings
    -0.16
    386
    -0.15
     engagements
    -0.15
    glass
    -0.15
     glass
    -0.15
    lements
    -0.14
    çİ»çĴĥ
    -0.14
     Benton
    -0.14
    aylight
    -0.14
     Bowen
    -0.14
    POSITIVE LOGITS
     leather
    0.32
     Leather
    0.29
     raw
    0.19
     hides
    0.18
     Raw
    0.17
    raw
    0.17
     dy
    0.16
     suede
    0.16
     saddle
    0.16
    ivor
    0.16
    Activations Density 0.034%

    No Known Activations