INDEX

Explanations

expressions of anticipation or impatience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

onder

-0.16

ry

-0.15

obble

-0.15

divider

-0.14

ãģĤ

-0.14

ichen

-0.14

usp

-0.14

erable

-0.14

áº¥p

-0.14

åĨł

-0.14

POSITIVE LOGITS

 imagine

0.17

orque

0.17

say

0.17

 tell

0.16

 fault

0.16

tell

0.16

saldo

0.16

 Fault

0.15

eva

0.15

eson

0.15

Activations Density 0.035%

expressions of anticipation or impatience

No Comments

No Known Activations