INDEX

Explanations

phrases and concepts related to topics or issues of significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

sans

-0.16

say

-0.16

sy

-0.15

esson

-0.15

som

-0.15

Ã¦nd

-0.15

lates

-0.14

ancements

-0.14

mas

-0.14

Ã³st

-0.14

POSITIVE LOGITS

abase

0.16

sembly

0.16

 prostitu

0.16

umat

0.15

Ã¤Ã¤

0.14

upp

0.14

ause

0.14

ailed

0.14

fluid

0.14

ARRY

0.14

Activations Density 0.017%

phrases and concepts related to topics or issues of significance

No Comments

No Known Activations