INDEX

Explanations

the phrase "in" indicating location or context within various situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

folios

-0.16

 ÑĤÐµÐ½

-0.14

addock

-0.14

Ã©ro

-0.14

ufen

-0.14

 Verg

-0.14

ÂŁ

-0.14

elves

-0.13

ierz

-0.13

à¸Ĺà¸¢

-0.13

POSITIVE LOGITS

,:,

0.16

Ð¾Ð²Ð°ÑĢÐ¸

0.16

rome

0.15

dur

0.14

anner

0.14

arios

0.13

Éµ

0.13

 Worm

0.13

redi

0.13

 '';č↵

0.13

Activations Density 0.032%

the phrase "in" indicating location or context within various situations

No Comments

No Known Activations