© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 20485
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "Washington Post"

    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
    krit
    -0.15
     republic
    -0.15
    æģĴ
    -0.15
     simp
    -0.14
    arch
    -0.14
     Scient
    -0.14
    irim
    -0.14
    bras
    -0.14
    /layouts
    -0.13
    (Have
    -0.13
    POSITIVE LOGITS
    oba
    0.19
    cken
    0.16
    .cn
    0.16
    ì§Ī
    0.15
    iazza
    0.15
     Yok
    0.15
    egend
    0.14
    ontent
    0.14
    æī¿
    0.14
    -quote
    0.14
    Activations Density 0.007%

    No Known Activations