© 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. 28-LLAMASCOPE-RES-32K
    11. 20367
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or contributions within a collaborative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.15
     experimented
    -0.15
     pioneered
    -0.14
    ivable
    -0.14
    shal
    -0.14
     Backbone
    -0.14
     resumed
    -0.14
    ertext
    -0.13
    erten
    -0.13
     аж
    -0.13
    POSITIVE LOGITS
     wanted
    0.41
    wanted
    0.39
     needed
    0.31
     Wanted
    0.28
    needed
    0.27
     Needed
    0.26
    Needed
    0.25
     knew
    0.25
     decided
    0.24
     felt
    0.24
    Activations Density 0.305%

    No Known Activations