INDEX

Explanations

references to labels in various contexts

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

ed

-0.20

edb

-0.17

falls

-0.17

umble

-0.17

urement

-0.16

UMB

-0.16

edir

-0.16

umb

-0.15

edu

-0.15

ya

-0.15

POSITIVE LOGITS

led

0.45

LED

0.23

lica

0.22

LING

0.21

ValuePair

0.21

ledon

0.20

icious

0.19

ë¡ľ

0.19

lico

0.19

ings

0.18

Activations Density 0.017%

references to labels in various contexts

No Comments

No Known Activations