INDEX

Explanations

references to locations and cemeteries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ores

-0.15

ends

-0.15

ÑĳÐ»

-0.14

ìĦłìĿĦ

-0.14

åĦ¿

-0.13

icity

-0.13

OrNull

-0.13

abus

-0.13

OrDefault

-0.13

Bounding

-0.13

POSITIVE LOGITS

Ã©mon

0.18

riba

0.16

abwe

0.15

 kÃ¸benhavn

0.15

imon

0.15

fox

0.15

LayoutConstraint

0.15

Ã¦nd

0.15

abbo

0.14

inputEmail

0.14

Activations Density 0.037%

references to locations and cemeteries

No Comments

No Known Activations