INDEX

Explanations

phrases that indicate recommendations or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

amarin

-0.20

chts

-0.15

gro

-0.15

agara

-0.15

ertz

-0.14

omo

-0.14

eyed

-0.14

ustr

-0.14

 âĨĶ

-0.14

POSITIVE LOGITS

orney

0.16

PackageManager

0.14

 poil

0.14

arro

0.14

encial

0.14

ocop

0.14

ogui

0.14

elog

0.14

CodeGen

0.13

hle

0.13

Activations Density 0.020%

phrases that indicate recommendations or conclusions

No Comments

No Known Activations