© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    references to identification documents or identification-related terms

    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
    -ton
    -0.16
    ÃŃ
    -0.15
    pton
    -0.15
     Warn
    -0.14
    pit
    -0.14
     harm
    -0.14
    ono
    -0.14
     Beit
    -0.14
    inya
    -0.14
    IGHL
    -0.14
    POSITIVE LOGITS
    erif
    0.17
    edl
    0.17
    eniable
    0.16
    oui
    0.15
    atica
    0.15
    еÑĢÑĤа
    0.15
    ζÏĮ
    0.15
    زاÙĨ
    0.14
    ewire
    0.14
    cloak
    0.14
    Activations Density 0.011%

    No Known Activations