INDEX

Explanations

quotes or reported speech within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ìī

-0.15

 Patel

-0.15

ItemAt

-0.15

 Nigeria

-0.15

 Mumbai

-0.14

arendra

-0.14

avs

-0.14

 Niger

-0.14

entin

-0.13

atha

-0.13

POSITIVE LOGITS

 Laos

0.17

inky

0.16

 foreigners

0.16

 Cambodia

0.16

Ph

0.15

 Kingdom

0.15

roy

0.15

 Camb

0.15

aÃ±

0.15

Ph

0.15

Activations Density 0.013%

quotes or reported speech within the text

No Comments

No Known Activations