INDEX

Explanations

proper nouns, particularly names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

afil

-0.16

CharCode

-0.16

.seed

-0.15

NIL

-0.15

Trap

-0.14

 peru

-0.14

 KÃ¼r

-0.14

yb

-0.14

eree

-0.14

æ¨

-0.14

POSITIVE LOGITS

uji

0.16

acha

0.14

umen

0.14

ãĤ¶ãĥ¼

0.14

rl

0.14

0.13

iji

0.13

Ele

0.13

Activations Density 0.032%

proper nouns, particularly names of people and places

No Comments

No Known Activations