INDEX

Explanations

the term "end" 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

adb

-0.17

ests

-0.17

erif

-0.16

adies

-0.16

iele

-0.15

eration

-0.15

est

-0.15

PRINTF

-0.14

compat

-0.14

ujte

-0.14

POSITIVE LOGITS

urance

0.24

owed

0.24

ocrine

0.23

emic

0.21

angered

0.20

odont

0.20

uring

0.20

orses

0.20

ors

0.19

orse

0.19

Activations Density 0.018%

the term "end" in various contexts

No Comments

No Known Activations