INDEX

Explanations

occurrences of the word "ded" in various forms

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

eller

-0.17

eliness

-0.15

 Townsend

-0.15

lette

-0.15

amient

-0.14

.Pin

-0.14

Ð»Ð°Ð²Ð°

-0.14

.pref

-0.14

 ÙģÙĩØ±Ø³Øª

-0.14

apers

-0.14

POSITIVE LOGITS

icated

0.28

uced

0.25

icates

0.23

ication

0.23

ded

0.22

uctions

0.22

alus

0.22

ded

0.22

Ded

0.22

uct

0.21

Activations Density 0.006%

occurrences of the word "ded" in various forms

No Comments

No Known Activations