© 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. 8-LLAMASCOPE-RES-32K
    11. 3517
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to control flow statements, particularly switches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeau
    -0.16
     Cummings
    -0.15
    Ïįν
    -0.15
    ehler
    -0.14
    onto
    -0.14
    nia
    -0.14
    μμ
    -0.14
    redients
    -0.14
    ertz
    -0.14
    quests
    -0.13
    POSITIVE LOGITS
    æ¯Ĵ
    0.16
    uche
    0.16
    adero
    0.15
     fin
    0.14
     minimum
    0.14
     toxic
    0.14
    hart
    0.14
    ess
    0.14
    erp
    0.14
    ance
    0.13
    Activations Density 0.007%

    No Known Activations