INDEX

Explanations

expressions of appreciation or acknowledgment for the work done on a blog

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ello

-0.17

 Matters

-0.14

uffer

-0.14

ults

-0.14

leh

-0.14

ÙĪØ´

-0.14

atches

-0.14

Å¥

-0.13

ÅĻÃŃm

-0.13

zik

-0.13

POSITIVE LOGITS

ertiary

0.15

chez

0.15

 Sentry

0.14

sey

0.14

ernity

0.14

ëŀĮ

0.14

iage

0.14

aire

0.14

erte

0.14

sav

0.14

Activations Density 0.002%

expressions of appreciation or acknowledgment for the work done on a blog

No Comments

No Known Activations