© 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. 20-LLAMASCOPE-RES-32K
    11. 24198
    Prev
    Next
    INDEX
    Explanations

    references to charitable actions and fundraising activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymoon
    -0.16
    DMIN
    -0.16
    zel
    -0.15
    _closure
    -0.15
    zzo
    -0.14
    izzo
    -0.13
    eton
    -0.13
    xit
    -0.13
    -radius
    -0.13
    floating
    -0.13
    POSITIVE LOGITS
     charities
    0.42
     charity
    0.39
     causes
    0.30
     charitable
    0.29
     organizations
    0.28
     Charity
    0.27
     organisations
    0.23
     children
    0.23
     Char
    0.23
    char
    0.23
    Activations Density 0.246%

    No Known Activations