INDEX

Explanations

phrases related to structured groups or entities 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 @ 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

ERCHANT

-0.15

ÑģÑĤÑĢÑĥ

-0.14

regor

-0.14

avad

-0.14

uddy

-0.14

 Demp

-0.14

@dynamic

-0.14

lip

-0.14

-alist

-0.14

-ln

-0.13

POSITIVE LOGITS

rd

0.29

-quarters

0.23

../../../

0.18

fold

0.17

rd

0.16

-four

0.16

resents

0.15

.rd

0.15

(rd

0.15

peat

0.15

Activations Density 0.112%

phrases related to structured groups or entities in various contexts

No Comments

No Known Activations