© 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. 18-LLAMASCOPE-RES-32K
    11. 28447
    Prev
    Next
    INDEX
    Explanations

    phrases that exhibit admiration or positive sentiment towards topics, using a specific grammatical structure involving articles and exclamatory expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atura
    -0.17
     Shed
    -0.15
    oku
    -0.15
    undy
    -0.15
     Graz
    -0.14
    pute
    -0.14
    ista
    -0.14
    ÑĨÑĥ
    -0.14
    273
    -0.14
    ắt
    -0.14
    POSITIVE LOGITS
     difference
    0.17
    ehr
    0.17
     pity
    0.17
    eck
    0.16
     shame
    0.16
    contrast
    0.16
     contrast
    0.16
     coincidence
    0.15
     waste
    0.15
    sis
    0.15
    Activations Density 0.010%

    No Known Activations