INDEX

Explanations

sequences of alphanumeric characters or coding notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ynet

-0.15

fas

-0.15

js

-0.14

 Hath

-0.13

ktop

-0.13

amet

-0.13

ikes

-0.13

Ðĥ

-0.13

ure

-0.13

 stiff

-0.13

POSITIVE LOGITS

activex

0.15

riott

0.14

zdy

0.14

 Ulus

0.14

ÐµÐ³Ð¾ÑĢ

0.14

afd

0.14

ucz

0.14

.scalablytyped

0.14

berger

0.14

INLINE

0.14

Activations Density 0.014%

sequences of alphanumeric characters or coding notations

No Comments

No Known Activations