© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 13590
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to toxicity and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redi
    -0.17
     therapies
    -0.14
    atron
    -0.14
     fmap
    -0.14
     escorte
    -0.14
     Prelude
    -0.14
    ¶Į
    -0.14
    çĭ¼
    -0.13
     Falk
    -0.13
    reet
    -0.13
    POSITIVE LOGITS
     OECD
    0.26
     endpoints
    0.24
    endpoint
    0.23
     endpoint
    0.23
     Partition
    0.21
     Endpoint
    0.20
     partition
    0.20
     acute
    0.19
    acute
    0.19
     chronic
    0.18
    Activations Density 0.012%

    No Known Activations