INDEX

Explanations

phrases indicating companionship or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

éļĨ

-0.16

.Typed

-0.15

zeug

-0.15

ks

-0.14

 corres

-0.14

çĹ

-0.14

Å¡ak

-0.13

 corresponding

-0.13

POSITIVE LOGITS

ieri

0.18

ignon

0.17

PCP

0.15

ecome

0.14

ulty

0.14

.nd

0.14

mav

0.14

iani

0.14

Ã¶ff

0.14

ATAL

0.14

Activations Density 0.080%

phrases indicating companionship or relationships

No Comments

No Known Activations