© 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. 23462
    Prev
    Next
    INDEX
    Explanations

    words with specific vowel combinations or phonetic patterns

    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
    jt
    -0.18
    jun
    -0.15
    okus
    -0.15
    зÑĭ
    -0.15
    jte
    -0.15
    zew
    -0.15
    aviour
    -0.15
    ollen
    -0.14
    й
    -0.14
    anse
    -0.14
    POSITIVE LOGITS
    issance
    0.29
    e
    0.21
    eum
    0.21
    ughty
    0.19
    id
    0.18
    o
    0.18
    conda
    0.17
    eus
    0.17
    ive
    0.17
    atik
    0.17
    Activations Density 0.054%

    No Known Activations