INDEX

Explanations

nouns and articles related to significant concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 itself

-0.17

Äħd

-0.16

sert

-0.15

ç¹ģ

-0.15

atten

-0.14

readcr

-0.14

//=

-0.14

itchen

-0.13

bai

-0.13

hv

-0.13

POSITIVE LOGITS

tring

0.15

íģ¼

0.15

æŀļ

0.14

irit

0.14

aj

0.14

ê¸Ī

0.14

ä»²

0.14

Irr

0.14

zes

0.13

 Horton

0.13

Activations Density 0.532%

nouns and articles related to significant concepts or entities

No Comments

No Known Activations