INDEX

Explanations

words related to monitoring or tracking activities and performance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iyat

-0.17

zed

-0.16

PyObject

-0.16

ogo

-0.16

onna

-0.15

yah

-0.15

ohen

-0.14

Äįet

-0.14

uu

-0.14

etrofit

-0.14

POSITIVE LOGITS

amac

0.18

nowled

0.15

ball

0.15

aden

0.15

ercul

0.15

vik

0.13

anos

0.13

.Reporting

0.13

bars

0.13

isu

0.13

Activations Density 0.018%

words related to monitoring or tracking activities and performance

No Comments

No Known Activations