INDEX

Explanations

references to visual elements, such as captions and figures, in 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

acock

-0.16

enso

-0.15

ahoma

-0.14

dfs

-0.14

AFE

-0.14

edith

-0.14

fds

-0.13

ê°ĳ

-0.13

IDX

-0.13

 ÐĵÐ¾Ð»Ð¾Ð²

-0.13

POSITIVE LOGITS

 caption

0.21

-caption

0.20

ì§

0.19

 figure

0.17

caption

0.16

 Caption

0.16

Caption

0.15

kening

0.15

 legend

0.15

 sizing

0.15

Activations Density 0.090%

references to visual elements, such as captions and figures, in the text

No Comments

No Known Activations