INDEX

Explanations

intense descriptors related to strength or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

onas

-0.16

ãĥ¼ãĥĦ

-0.15

iram

-0.15

rella

-0.15

enance

-0.14

plevel

-0.14

.scalablytyped

-0.14

.nd

-0.14

ichern

-0.14

POSITIVE LOGITS

yw

0.17

 Howell

0.16

ereg

0.15

 Kong

0.15

-pencil

0.14

getSession

0.14

à¥ģà¤Ł

0.13

right

0.13

 conven

0.13

Activations Density 0.006%

intense descriptors related to strength or intensity

No Comments

No Known Activations