© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 14137
    Prev
    Next
    INDEX
    Explanations

    specific vocabulary related to evaluations or descriptions of actions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ano
    -0.15
    iets
    -0.15
    arged
    -0.14
    utes
    -0.14
    oplevel
    -0.14
    @a
    -0.13
     thôi
    -0.13
    oho
    -0.13
    asper
    -0.12
    ãĥ³ãĥĩãĤ£
    -0.12
    POSITIVE LOGITS
     fact
    0.24
    uario
    0.17
    fact
    0.16
     manner
    0.16
    inya
    0.15
    vise
    0.15
    γοÏħ
    0.15
    idon
    0.15
     اÛĮÙĨÚ©Ùĩ
    0.14
    ĵ¨
    0.14
    Activations Density 0.242%

    No Known Activations