© 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. 2-LLAMASCOPE-RES-32K
    11. 2995
    Prev
    Next
    INDEX
    Explanations

    words that reflect actions or processes, particularly those ending in 'ing' and variations of the word 'way'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃky
    -0.16
    ered
    -0.14
    orns
    -0.14
    ng
    -0.14
    cion
    -0.14
    iek
    -0.14
    etak
    -0.14
    -fontawesome
    -0.13
    gel
    -0.13
    (^
    -0.13
    POSITIVE LOGITS
    597
    0.16
     CLUB
    0.15
    ittest
    0.15
    èįī
    0.15
    óst
    0.14
    برÛĮ
    0.14
    verb
    0.14
     bail
    0.14
    uba
    0.13
     club
    0.13
    Activations Density 0.006%

    No Known Activations