INDEX

Explanations

programming-related dictionary 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ullan

-0.17

flo

-0.15

LEAN

-0.15

cmc

-0.14

cci

-0.14

áº¡ch

-0.14

rens

-0.14

Ð¾Ð²ÑĸÐ´

-0.14

 encoder

-0.13

_ATT

-0.13

POSITIVE LOGITS

NR

0.31

NR

0.30

NF

0.29

NF

0.27

ORS

0.24

OF

0.22

FS

0.22

 gens

0.21

 getline

0.21

awk

0.21

Activations Density 0.001%

programming-related dictionary syntax and operations

No Comments

No Known Activations