INDEX

Explanations

references to interviews and discussions about careers and professional experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ebe

-0.17

aea

-0.16

 Malone

-0.16

 Meredith

-0.15

rung

-0.15

eya

-0.15

æ¯ķ

-0.15

zes

-0.15

 Brace

-0.15

entes

-0.14

POSITIVE LOGITS

arges

0.16

inet

0.15

æĮ

0.14

.tif

0.14

oux

0.14

orate

0.14

ç¦®

0.14

 ÑĤÐ¾Ð¼

0.14

upy

0.14

Activations Density 0.743%

references to interviews and discussions about careers and professional experiences

No Comments

No Known Activations