INDEX

Explanations

phrases related to making assumptions or beliefs about others' intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

erman

-0.18

esian

-0.18

essler

-0.17

rome

-0.16

etting

-0.16

udas

-0.15

Ø©

-0.15

osl

-0.15

Assert

-0.15

ness

-0.15

POSITIVE LOGITS

ably

0.23

/assert

0.22

ptions

0.19

 Worst

0.17

nal

0.17

PTION

0.16

ptive

0.16

ively

0.16

 worst

0.16

Activations Density 0.026%

phrases related to making assumptions or beliefs about others' intentions

No Comments

No Known Activations