© 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. 1-LLAMASCOPE-RES-32K
    11. 16089
    Prev
    Next
    INDEX
    Explanations

    mentions of "sidelines" or related terms indicating something or someone being out of action or off the main focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICA
    -0.15
    habit
    -0.15
     lombok
    -0.15
     rem
    -0.15
    (QtCore
    -0.14
    434
    -0.14
    AGR
    -0.14
    ä¹³
    -0.14
    ly
    -0.14
    ica
    -0.14
    POSITIVE LOGITS
    alama
    0.16
    ücü
    0.15
    urope
    0.14
    าà¸į
    0.14
     GANG
    0.14
     Roose
    0.14
    ennon
    0.14
    ÅĽcie
    0.14
     Fur
    0.14
    $core
    0.14
    Activations Density 0.001%

    No Known Activations