INDEX

Explanations

specific structured formats in the text, particularly those resembling URLs or navigation links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 ØµÙĨ

-0.15

amat

-0.14

(Seq

-0.14

ç±

-0.14

Ð¾Ð½Ð´

-0.13

inas

-0.13

bin

-0.13

arah

-0.13

;;;;

-0.13

 Scient

-0.13

POSITIVE LOGITS

Ny

0.18

ny

0.17

ochen

0.16

anches

0.16

NY

0.15

patch

0.15

ial

0.15

 parch

0.14

ected

0.14

adero

0.14

Activations Density 0.000%

specific structured formats in the text, particularly those resembling URLs or navigation links

No Comments

No Known Activations