INDEX

Explanations

phrases suggesting directives or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĤīãģĽ

-0.16

ylie

-0.15

iders

-0.15

strain

-0.15

rimon

-0.15

vero

-0.15

ilty

-0.14

ulet

-0.14

tplib

-0.14

venir

-0.14

POSITIVE LOGITS

ifer

0.16

 voks

0.16

inal

0.15

use

0.14

atta

0.14

ito

0.14

mind

0.14

sing

0.13

FTA

0.13

Activations Density 0.074%

phrases suggesting directives or instructions

No Comments

No Known Activations