INDEX

Explanations

contrasts between external appearances and internal qualities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

atel

-0.17

ungal

-0.15

 Peripheral

-0.14

.Accessible

-0.14

 globally

-0.14

wide

-0.13

ungi

-0.13

kud

-0.13

out

-0.13

 paran

-0.13

POSITIVE LOGITS

 inside

1.07

 Inside

0.98

Inside

0.95

inside

0.94

 interior

0.80

_inside

0.79

 Ð²Ð½ÑĥÑĤÑĢÐ¸

0.68

åĨħéĥ¨

0.67

åĨħ

0.65

 interiors

0.64

Activations Density 0.383%

contrasts between external appearances and internal qualities or conditions

No Comments

No Known Activations