INDEX

Explanations

occurrences of the word "highlight" and its variations 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ehler

-0.18

Erk

-0.15

jac

-0.15

ugh

-0.15

aggi

-0.14

osti

-0.14

Ø®Ø§ÙĨÙĩ

-0.14

uve

-0.14

åĿĬ

-0.14

astr

-0.13

POSITIVE LOGITS

Î¬ÏĤ

0.15

bread

0.15

ened

0.15

íĮħ

0.14

 Division

0.14

ãĥ¥

0.14

NewLabel

0.14

elsea

0.13

fait

0.13

Activations Density 0.019%

occurrences of the word "highlight" and its variations in the text

No Comments

No Known Activations