INDEX

Explanations

references to abortion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

hta

-0.17

Äįel

-0.15

otas

-0.15

opher

-0.15

tha

-0.15

ying

-0.14

å®³

-0.14

ä¾

-0.14

ices

-0.14

itional

-0.14

POSITIVE LOGITS

STRACT

0.22

igail

0.20

AB

0.20

stractions

0.19

Ab

0.19

(ab

0.19

ab

0.19

andoned

0.19

original

0.19

 init

0.18

Activations Density 0.028%

references to abortion

No Comments

No Known Activations