INDEX

Explanations

terms related to minimum and maximum values in programming or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

atrix

-0.19

.Void

-0.15

odu

-0.15

 graveyard

-0.14

iated

-0.14

ispecies

-0.14

 Candle

-0.13

Ð¾Ð¶Ðµ

-0.13

replacement

-0.13

bare

-0.13

POSITIVE LOGITS

udo

0.19

gon

0.15

sdale

0.15

orie

0.14

-case

0.14

yth

0.14

 depression

0.13

ower

0.13

.ManyToMany

0.13

Ã±ana

0.13

Activations Density 0.028%

terms related to minimum and maximum values in programming or mathematical contexts

No Comments

No Known Activations