INDEX

Explanations

specific nouns related to various categories such as vehicles, biological strains, and dishes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ioned

-0.15

LE

-0.15

ades

-0.14

 Lanc

-0.14

YYY

-0.14

LEN

-0.13

 Vanguard

-0.13

Glo

-0.13

ted

-0.13

POSITIVE LOGITS

éº¦

0.15

igr

0.15

imple

0.15

 Zaman

0.14

dek

0.14

 ÑĸÐ½ÑĪÐ¾Ð³Ð¾

0.14

ÙħÙĦØ©

0.14

urge

0.14

lifetime

0.14

InRange

0.13

Activations Density 0.370%

specific nouns related to various categories such as vehicles, biological strains, and dishes

No Comments

No Known Activations