INDEX

Explanations

phrases related to absence and presence 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

uja

-0.15

ige

-0.14

ocy

-0.12

ATUS

-0.12

ait

-0.12

ÙĦØ¹

-0.12

cia

-0.11

uel

-0.11

ule

-0.11

ixin

-0.11

POSITIVE LOGITS

 such

0.16

 this

0.16

 that

0.16

two

0.15

 some

0.15

 something

0.14

any

0.14

one

0.14

 these

0.14

 another

0.14

Activations Density 0.659%

phrases related to absence and presence in various contexts

No Comments

No Known Activations