INDEX

Explanations

terms and concepts related to vertical structures and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ulis

-0.15

lay

-0.14

 Sage

-0.14

ecess

-0.14

map

-0.14

wre

-0.14

erse

-0.14

InputStream

-0.14

POSITIVE LOGITS

 stairs

0.19

 tower

0.18

 tallest

0.17

æ¢¯

0.16

(#)

0.16

-rise

0.16

endas

0.15

 staircase

0.15

 tall

0.15

 shaft

0.15

Activations Density 0.213%

terms and concepts related to vertical structures and dimensions

No Comments

No Known Activations