INDEX

Explanations

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

apus

-0.18

onde

-0.14

ansa

-0.14

à¤¾à¤µà¤¨

-0.14

Lim

-0.14

ying

-0.14

rella

-0.14

-0.13

agos

-0.13

ucci

-0.13

POSITIVE LOGITS

 behalf

0.38

 occasion

0.20

etime

0.19

 basis

0.18

eway

0.18

ission

0.17

occasion

0.17

 konci

0.17

esh

0.16

look

0.16

Activations Density 0.159%

occurrences of the word "the"

No Comments

No Known Activations