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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 18642
    Prev
    Next
    INDEX
    Explanations

    elements related to community support and essential workers during challenging times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.15
    оваÑĢ
    -0.14
    uegos
    -0.14
     Ñıк
    -0.14
    ekim
    -0.13
     åıĪ
    -0.13
     departing
    -0.13
     Present
    -0.13
    aspers
    -0.13
    WRAPPER
    -0.13
    POSITIVE LOGITS
     works
    0.23
     hadn
    0.22
     lives
    0.22
     said
    0.20
     wasn
    0.19
     estimates
    0.18
     remembers
    0.18
     vivid
    0.17
     woke
    0.16
    (ph
    0.16
    Activations Density 0.171%

    No Known Activations