INDEX

Explanations

key terms and phrases indicating actions or conditions related to existence and implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

UGHT

-0.15

zw

-0.14

ercial

-0.14

inea

-0.14

ito

-0.14

essen

-0.14

erval

-0.14

edik

-0.14

.authenticate

-0.14

 reconc

-0.13

POSITIVE LOGITS

ICLE

0.15

 Besch

0.14

arcy

0.14

 suspension

0.13

vana

0.13

Bam

0.13

ÑģÑĤÐ¸Ñĩ

0.13

ī

0.13

umat

0.13

á»įng

0.13

Activations Density 0.030%

key terms and phrases indicating actions or conditions related to existence and implications

No Comments

No Known Activations