INDEX

Explanations

computer programming terminology and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

lector

-0.16

_contin

-0.15

azon

-0.15

lectron

-0.15

bilt

-0.14

ÙħØ¯Ø©

-0.14

ìĿ´ëĵľ

-0.14

gence

-0.14

 ÙĤØ¯Ø±

-0.14

-0.13

POSITIVE LOGITS

si

0.15

 amac

0.15

gratis

0.15

iw

0.14

 Rubin

0.14

hol

0.14

ivic

0.14

rus

0.14

AXB

0.14

 diss

0.14

Activations Density 0.242%

computer programming terminology and data structures

No Comments

No Known Activations