INDEX

Explanations

phrases related to acquisition or receiving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

olf

-0.16

 bottoms

-0.14

Ð·Ñĥ

-0.14

 Stef

-0.14

 nobody

-0.14

eno

-0.14

opaque

-0.13

un

-0.13

ugh

-0.13

POSITIVE LOGITS

oire

0.18

chas

0.16

estar

0.16

ENTE

0.15

ëł¨

0.15

tlement

0.15

 Darling

0.15

ekt

0.15

ascus

0.14

loyd

0.14

Activations Density 0.132%

phrases related to acquisition or receiving something

No Comments

No Known Activations