INDEX

Explanations

phrases indicating direct communication and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ehler

-0.19

eniz

-0.16

Ø§ÙĦØ§Øª

-0.16

-0.15

opoulos

-0.15

 sodom

-0.15

ussen

-0.15

 Leak

-0.14

.med

-0.14

gae

-0.14

POSITIVE LOGITS

Modifiers

0.15

 brides

0.14

upos

0.14

quis

0.14

lim

0.14

wed

0.14

/functions

0.14

liÄį

0.14

wed

0.13

hon

0.13

Activations Density 0.000%

phrases indicating direct communication and assistance

No Comments

No Known Activations