INDEX

Explanations

references to dictionaries or scholarly texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ð³Ð¾ÑĢÐ¾Ð´

-0.15

rez

-0.15

á»ĩu

-0.14

Ïį

-0.14

uyÃªn

-0.14

allon

-0.14

á»ķ

-0.13

ylene

-0.13

enga

-0.13

xffffff

-0.13

POSITIVE LOGITS

Bundle

0.16

orna

0.15

rys

0.14

INGER

0.14

.nih

0.13

addy

0.13

ãĥĭãĥĥãĤ¯

0.13

ogene

0.13

Ã¡rio

0.13

inger

0.13

Activations Density 0.012%

references to dictionaries or scholarly texts

No Comments

No Known Activations