© 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. 12-LLAMASCOPE-RES-32K
    11. 29799
    Prev
    Next
    INDEX
    Explanations

    references to variety and differences in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hip
    -0.16
    anne
    -0.16
    ote
    -0.15
    ittest
    -0.15
    uet
    -0.15
    hog
    -0.15
    اÙĨÙĩ
    -0.14
    ses
    -0.14
    imet
    -0.14
    iliary
    -0.14
    POSITIVE LOGITS
    iating
    0.30
    ially
    0.28
    iability
    0.23
    iates
    0.22
    ials
    0.21
    iator
    0.20
     kinds
    0.20
    iators
    0.20
    -sex
    0.20
    iale
    0.17
    Activations Density 0.053%

    No Known Activations