INDEX

Explanations

occurrences of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

APON

-0.15

OnInit

-0.15

illage

-0.15

Persistence

-0.15

RootElement

-0.15

REFERRED

-0.14

sic

-0.14

Ð¾Ð»Ð¾ÑĪ

-0.14

aginator

-0.14

atrix

-0.14

POSITIVE LOGITS

atown

0.17

alty

0.15

iyat

0.14

olah

0.14

ousel

0.14

oufl

0.14

ocab

0.13

osu

0.13

ehler

0.13

 Bout

0.13

Activations Density 0.007%

occurrences of the word "of."

No Comments

No Known Activations