© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 12684
    Prev
    Next
    INDEX
    Explanations

    references to safety and security in societal contexts

    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
    itan
    -0.15
     pig
    -0.15
    ulous
    -0.15
    pig
    -0.15
    ersiz
    -0.14
     Pig
    -0.14
     pigs
    -0.14
    елеÑĦ
    -0.14
    lund
    -0.14
    undle
    -0.14
    POSITIVE LOGITS
     hitch
    0.17
     interfaces
    0.16
     interface
    0.15
    _ASCII
    0.15
    ware
    0.15
     INTERFACE
    0.15
     mop
    0.15
     enumeration
    0.15
    ucc
    0.14
     enlightenment
    0.14
    Activations Density 0.029%

    No Known Activations