© 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. 4-LLAMASCOPE-RES-32K
    11. 31071
    Prev
    Next
    INDEX
    Explanations

    keywords related to Scottish independence and its political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scripts
    -0.16
    htm
    -0.15
    lier
    -0.15
    iggers
    -0.14
     Cro
    -0.14
    rzy
    -0.14
    513
    -0.14
     script
    -0.14
    .Ptr
    -0.14
     tam
    -0.14
    POSITIVE LOGITS
    alg
    0.16
    andex
    0.16
    qed
    0.15
    meer
    0.15
    zem
    0.15
    ReuseIdentifier
    0.14
    Boss
    0.14
     Boss
    0.14
    xab
    0.14
    ENDER
    0.14
    Activations Density 0.027%

    No Known Activations