INDEX

Explanations

the word "that" in various contexts

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

ia

-0.15

ach

-0.15

arus

-0.15

ith

-0.14

uest

-0.14

 commissions

-0.14

oki

-0.14

-0.13

é¡Ķ

-0.13

oph

-0.13

POSITIVE LOGITS

ãĥ³ãĥĳ

0.18

iesen

0.16

ANGO

0.15

à¸²à¸°

0.14

jid

0.14

.metamodel

0.14

 èģ

0.14

 ÐĳÐ¾ÑĢ

0.14

rdf

0.14

_EV

0.14

Activations Density 0.042%

the word "that" in various contexts

No Comments

No Known Activations