© 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. 24-LLAMASCOPE-RES-32K
    11. 13630
    Prev
    Next
    INDEX
    Explanations

    references to advertising and promotional activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¾Ľ
    -0.14
    anax
    -0.13
    ifix
    -0.13
    rary
    -0.13
    inne
    -0.13
    oje
    -0.12
    rips
    -0.12
    _SYS
    -0.12
    -sc
    -0.12
    osc
    -0.12
    POSITIVE LOGITS
     marketing
    0.78
     Marketing
    0.68
    marketing
    0.64
    Marketing
    0.63
     advertising
    0.62
     promotion
    0.60
     promotional
    0.54
     Advertising
    0.53
     Promotion
    0.52
    Advertising
    0.50
    Activations Density 0.621%

    No Known Activations