INDEX

Explanations

phrases related to blocking or obstruction

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

ulfilled

-0.16

ves

-0.15

ming

-0.15

ÄħÅ¼

-0.15

ä¸įåĪ°

-0.14

vem

-0.14

ÌĨ

-0.14

ux

-0.14

TY

-0.13

POSITIVE LOGITS

busters

0.19

enheim

0.17

chains

0.17

quote

0.17

buster

0.16

pedia

0.16

stant

0.16

 tuá»ķi

0.16

aded

0.15

pipes

0.15

Activations Density 0.029%

phrases related to blocking or obstruction

No Comments

No Known Activations