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

    Neuronpedia

    Jacobian LensNEW
    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. 19-LLAMASCOPE-RES-32K
    11. 31544
    Prev
    Next
    INDEX
    Explanations

    references to organizations, roles, and individuals involved in discussions about societal and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اÙĦÙĪÙģ
    -0.14
    ely
    -0.14
    -present
    -0.14
    elib
    -0.14
    estroy
    -0.14
    onth
    -0.14
    _DECLARE
    -0.14
    fers
    -0.14
    igu
    -0.14
    bsp
    -0.14
    POSITIVE LOGITS
     tweeted
    0.15
    izedName
    0.15
    aida
    0.15
    alysis
    0.14
     ÙĪا
    0.14
    rana
    0.14
    деÑĢж
    0.14
     Glo
    0.14
    Reached
    0.14
     via
    0.14
    Activations Density 0.087%

    No Known Activations