© 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. 8-LLAMASCOPE-RES-32K
    11. 2173
    Prev
    Next
    INDEX
    Explanations

    instances of misfortune or accidents leading to harm or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umnos
    -0.17
     presente
    -0.15
    ObjectType
    -0.14
    prus
    -0.14
    ↵↵
    -0.14
     Bapt
    -0.14
    ikes
    -0.14
    /forum
    -0.13
    ãĥ³ãĤº
    -0.13
    Äł
    -0.13
    POSITIVE LOGITS
    legg
    0.15
     norm
    0.14
    Millis
    0.14
    945
    0.14
    âĢª
    0.14
    undle
    0.14
    sto
    0.14
    305
    0.14
    quisition
    0.14
    815
    0.14
    Activations Density 0.708%

    No Known Activations