INDEX

Explanations

references to individuals, particularly those with the name "Romero."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

aur

-0.17

urre

-0.16

ala

-0.16

pure

-0.16

 Steele

-0.15

uto

-0.15

peace

-0.14

metic

-0.14

imore

-0.14

LOB

-0.14

POSITIVE LOGITS

ount

0.15

jah

0.14

 spoiled

0.14

 Ø¹Ùħ

0.14

/releases

0.14

queen

0.14

beg

0.14

ceed

0.14

IFO

0.14

iddet

0.14

Activations Density 0.008%

references to individuals, particularly those with the name "Romero."

No Comments

No Known Activations