INDEX

Explanations

occurrences of the word "as" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑĢÐ°ÑĤÐ½Ð¾

-0.16

inho

-0.15

_UNDEFINED

-0.15

aded

-0.14

imedia

-0.14

notated

-0.13

ipel

-0.13

ftar

-0.13

ãģ¦ãĤĤ

-0.13

asl

-0.13

POSITIVE LOGITS

wel

0.20

YLON

0.19

well

0.18

-and

0.15

otonin

0.15

ÏģÎ¹Î½

0.15

west

0.14

 besides

0.14

 strerror

0.14

etro

0.14

Activations Density 0.056%

occurrences of the word "as" in various contexts

No Comments

No Known Activations