INDEX

Explanations

articles and possessive pronouns 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

]={↵

-0.14

ergus

-0.14

èĩ

-0.14

maj

-0.14

ibo

-0.14

agua

-0.13

ozem

-0.13

teki

-0.13

Î½Î¹

-0.13

Ã³sito

-0.13

POSITIVE LOGITS

anto

0.16

swire

0.16

ÑĢÐ¾ÑĤÐ¸Ð²

0.15

nor

0.14

orex

0.14

uni

0.13

/MIT

0.13

bis

0.13

esa

0.13

 Portions

0.13

Activations Density 1.159%

articles and possessive pronouns in the text

No Comments

No Known Activations