INDEX

Explanations

terms related to limitations and restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

kul

-0.15

oma

-0.15

escription

-0.15

à¸Ľà¸£à¸°à¸¡

-0.14

aison

-0.14

ald

-0.14

ounge

-0.14

leh

-0.14

els

-0.14

wm

-0.14

POSITIVE LOGITS

edImage

0.20

ìĤ¬íķŃ

0.19

conds

0.18

$MESS

0.16

ters

0.16

/conf

0.16

edList

0.16

 ìĤ¬íķŃ

0.16

edom

0.15

acci

0.15

Activations Density 0.044%

terms related to limitations and restrictions

No Comments

No Known Activations