INDEX

Explanations

contrasts or negations in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

uron

-0.16

à¤°à¤£

-0.15

venes

-0.15

aru

-0.14

atel

-0.14

esty

-0.14

enin

-0.14

qing

-0.14

 boarding

-0.14

rong

-0.14

POSITIVE LOGITS

esser

0.16

ape

0.16

êµ¬

0.15

ãĥĸãĥŃ

0.14

ÏģÎ¿

0.14

 ÐĿÐ°Ñģ

0.14

áº¯c

0.14

thon

0.14

 Lever

0.14

Activations Density 0.160%

contrasts or negations in statements

No Comments

No Known Activations