INDEX

Explanations

code structures or syntactical elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

VRT

-0.16

ometr

-0.16

theid

-0.15

ove

-0.15

-0.14

otto

-0.14

yny

-0.14

Ã©gor

-0.14

ppo

-0.14

POSITIVE LOGITS

Pil

0.18

ullet

0.16

 merc

0.15

 tabBar

0.15

Ku

0.14

 Glas

0.14

upal

0.14

 piles

0.14

Gly

0.14

pil

0.14

Activations Density 0.155%

code structures or syntactical elements

No Comments

No Known Activations