© 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. 14445
    Prev
    Next
    INDEX
    Explanations

    concepts related to leadership, career development, and community engagement

    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
    yle
    -0.18
    qa
    -0.16
    avi
    -0.16
    Hosting
    -0.15
    eland
    -0.15
    ici
    -0.15
    acha
    -0.15
    awi
    -0.14
     Dodd
    -0.14
    arte
    -0.14
    POSITIVE LOGITS
    æŁĦ
    0.16
    andas
    0.15
    zÄħd
    0.15
    žit
    0.14
    usra
    0.14
    Ậ
    0.14
    ustos
    0.14
     ansch
    0.14
    Âłtom
    0.14
    åħ·
    0.13
    Activations Density 0.122%

    No Known Activations