INDEX

Explanations

proper nouns related to locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

adelphia

-0.17

Ð¾ÑĢÐ°Ñı

-0.16

.scalablytyped

-0.15

 addCriterion

-0.15

ï»¿using

-0.14

edImage

-0.14

edb

-0.14

edReader

-0.14

senal

-0.13

Æ°á»£u

-0.13

POSITIVE LOGITS

0.18

Ùĳ

0.18

Î½ÏĦ

0.14

ERO

0.14

Â£Â£

0.14

Ã«r

0.14

bole

0.14

oux

0.13

most

0.13

its

0.13

Activations Density 1.315%

proper nouns related to locations and entities

No Comments

No Known Activations