INDEX

Explanations

geographic locations and related identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eza

-0.15

voj

-0.15

vere

-0.14

enga

-0.14

 Ð·ÐµÐ¼Ð»Ñı

-0.14

ffee

-0.14

Ð¼Ð°Ð·

-0.14

ysl

-0.14

adiens

-0.14

POSITIVE LOGITS

irts

0.14

 Various

0.13

hand

0.13

oky

0.13

aj

0.13

ugh

0.13

lg

0.13

 Hand

0.12

 Sponsored

0.12

Activations Density 0.078%

geographic locations and related identifiers

No Comments

No Known Activations