Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 21803
    Prev
    Next
    INDEX
    Explanations

    words related to allegations or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eler
    -0.17
    ler
    -0.17
    ault
    -0.17
    leigh
    -0.16
    older
    -0.16
    relude
    -0.16
    essim
    -0.15
    eldorf
    -0.15
    shal
    -0.15
    elyn
    -0.15
    POSITIVE LOGITS
    andro
    0.23
    querque
    0.20
    azeera
    0.18
    igned
    0.18
    zheimer
    0.17
    onso
    0.17
    ameda
    0.17
    phabet
    0.16
    ÙģØ§Øª
    0.16
    abeth
    0.16
    Activations Density 0.127%

    No Known Activations