INDEX

Explanations

proper nouns, particularly names associated with historical figures and notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ries

-0.17

-0.15

umed

-0.15

sis

-0.15

olia

-0.15

ordes

-0.14

orne

-0.14

orum

-0.14

ies

-0.13

POSITIVE LOGITS

uai

0.15

 fitte

0.15

æķ·

0.14

zad

0.14

/type

0.14

Tos

0.14

Ģìŀ¥

0.13

hots

0.13

inho

0.13

Ã¹y

0.13

Activations Density 0.113%

proper nouns, particularly names associated with historical figures and notable individuals

No Comments

No Known Activations