INDEX

Explanations

verbs indicating ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

:UITableView

-0.17

_BS

-0.16

agne

-0.14

åħĪçĶŁ

-0.14

ott

-0.14

amba

-0.14

arna

-0.14

issing

-0.14

ola

-0.14

iais

-0.14

POSITIVE LOGITS

to

0.23

ble

0.16

="{!!

0.16

ä¸ĭåİ»

0.15

nings

0.15

ØªØ§

0.15

entially

0.14

zar

0.14

Activations Density 0.040%

verbs indicating ongoing actions or processes

No Comments

No Known Activations