© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 22243
    Prev
    Next
    INDEX
    Explanations

    words related to exaggeration and marketing themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĴè¦ĭãĤĭ
    -0.17
    ozem
    -0.16
    â̦"↵↵
    -0.14
    â̦”↵↵
    -0.13
    ::*
    -0.13
     ())
    -0.13
     شاÙĩد
    -0.13
    CMD
    -0.13
    oulos
    -0.13
    ãĢıï¼Ī
    -0.13
    POSITIVE LOGITS
     anyone
    0.37
     FT
    0.34
     anybody
    0.32
     indeed
    0.29
    ?
    0.28
     ft
    0.27
     alert
    0.27
     =
    0.27
     Anyone
    0.26
    =yes
    0.24
    Activations Density 0.343%

    No Known Activations