© 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. 23-LLAMASCOPE-RES-32K
    11. 30874
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups identified as victims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ings
    -0.18
    erie
    -0.17
    enta
    -0.16
    egot
    -0.15
    oes
    -0.15
    mates
    -0.15
    ØŃÙĬ
    -0.15
    bons
    -0.15
    é¢ĺ
    -0.15
    ROS
    -0.15
    POSITIVE LOGITS
    hood
    0.25
    ized
    0.25
    /target
    0.20
    atically
    0.19
    ively
    0.19
    izers
    0.19
    ology
    0.19
    ization
    0.17
    IZED
    0.17
    ised
    0.16
    Activations Density 0.024%

    No Known Activations