INDEX

Explanations

phrases emphasizing key points or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Bench

-0.16

bench

-0.15

undi

-0.15

 Pager

-0.15

choices

-0.15

 Choices

-0.15

 choices

-0.14

hunt

-0.14

sla

-0.14

urst

-0.14

POSITIVE LOGITS

Ð¾Ð·ÐµÐ¼

0.17

kli

0.15

chie

0.15

Ã¡rio

0.14

reur

0.14

 LIST

0.14

 Ð²ÑĭÑħÐ¾Ð´

0.14

 listed

0.14

ãģıãĤĭ

0.14

è¾¦

0.14

Activations Density 0.397%

phrases emphasizing key points or arguments

No Comments

No Known Activations