INDEX

Explanations

programming-related syntax and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elu

-0.18

agus

-0.17

Ø¬Ø§Ø±

-0.16

-0.15

SEQU

-0.15

agos

-0.14

 hrom

-0.14

ais

-0.14

ALSE

-0.14

POSITIVE LOGITS

 negative

0.23

=-

0.23

 Negative

0.22

>-

0.21

>=

0.21

negative

0.21

Negative

0.20

npos

0.19

(-

0.19

-negative

0.18

Activations Density 0.072%

programming-related syntax and operations

No Comments

No Known Activations