INDEX

Explanations

references to addresses in various formats

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

zb

-0.16

ero

-0.16

cken

-0.16

isch

-0.15

ayo

-0.14

Ø²Ø§Ø±

-0.14

pty

-0.14

allest

-0.14

acock

-0.14

POSITIVE LOGITS

(es

0.23

istrovstvÃŃ

0.21

ses

0.20

íķĻ

0.15

unsupported

0.15

SES

0.15

Î¸ÎµÎ½

0.15

TES

0.14

ToSelector

0.14

Ø§ÙĦØ¹

0.14

Activations Density 0.019%

references to addresses in various formats

No Comments

No Known Activations