INDEX

Explanations

sentences with varying uses of "it" and "that"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

atisfied

-0.17

 neod

-0.15

aucoup

-0.14

Ã³b

-0.14

storybook

-0.14

repr

-0.14

:');↵

-0.14

rnek

-0.14

orer

-0.14

 Hats

-0.14

POSITIVE LOGITS

 occurred

0.22

 occurs

0.21

 kind

0.19

 occur

0.19

kind

0.19

 appears

0.18

Occ

0.18

 Freund

0.17

 ocor

0.17

Activations Density 0.182%

sentences with varying uses of "it" and "that"

No Comments

No Known Activations