INDEX

Explanations

titles or headings indicating the continuation of a sequence or series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 vuel

-0.15

avery

-0.15

ozor

-0.15

-0.14

è¸

-0.14

riel

-0.14

POSITIVE LOGITS

æ¨

0.15

ãĤīãģĹ

0.15

ìļķ

0.15

å®¶ä¼Ļ

0.15

ichni

0.14

acades

0.14

 Respir

0.14

.rev

0.14

chw

0.13

/problem

0.13

Activations Density 0.003%

titles or headings indicating the continuation of a sequence or series

No Comments

No Known Activations