INDEX

Explanations

expressions of dissatisfaction regarding products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inder

-0.16

ÙĨØ¯Ø±

-0.16

ibold

-0.16

mmo

-0.15

kili

-0.15

ãĥ³ãĤ¹

-0.14

oux

-0.14

ÏģÎ±Î²

-0.14

kin

-0.14

intree

-0.14

POSITIVE LOGITS

switch

0.26

 switching

0.26

 switch

0.26

 switched

0.25

 SWITCH

0.22

 Switch

0.22

 switches

0.22

-switch

0.21

.switch

0.21

 choice

0.21

Activations Density 0.146%

expressions of dissatisfaction regarding products or services

No Comments

No Known Activations