INDEX

Explanations

numeric values or identifiers associated with various elements, such as events or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ahat

-0.17

 Kons

-0.16

Ð¾Ð»ÑĮÐ·Ð¾Ð²Ð°ÑĤ

-0.16

til

-0.15

.deb

-0.14

zman

-0.14

 herr

-0.14

aud

-0.14

elman

-0.14

 blank

-0.14

POSITIVE LOGITS

anke

0.15

ACKET

0.15

alse

0.14

ÏĦÎ¿ÏħÏĤ

0.14

 ActionTypes

0.14

apter

0.14

etics

0.14

.cloud

0.14

Activations Density 0.030%

numeric values or identifiers associated with various elements, such as events or statistics

No Comments

No Known Activations