© 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. 7-LLAMASCOPE-RES-32K
    11. 21925
    Prev
    Next
    INDEX
    Explanations

    items relating to lists and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stad
    -0.16
    ä¹Ļ
    -0.15
     hôm
    -0.15
    anding
    -0.14
    avl
    -0.14
    |max
    -0.14
    marked
    -0.14
    ophile
    -0.13
    arakter
    -0.13
    ilet
    -0.13
    POSITIVE LOGITS
    gba
    0.15
     Gam
    0.15
    arnation
    0.14
    Gam
    0.14
    egl
    0.14
    ãĥ¼ãĥľ
    0.14
    ORIA
    0.14
    InSection
    0.14
    unte
    0.14
    nia
    0.13
    Activations Density 0.004%

    No Known Activations