INDEX

Explanations

instances of the letter 'O' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 repro

-0.15

ugu

-0.15

ocular

-0.14

cca

-0.14

kes

-0.14

nya

-0.14

à¸ģ

-0.14

ven

-0.13

eries

-0.13

POSITIVE LOGITS

ehler

0.15

oze

0.15

ymb

0.15

iginal

0.14

ubre

0.14

ensed

0.14

maz

0.14

è®¸

0.14

ltre

0.14

ÏħÎº

0.14

Activations Density 0.077%

instances of the letter 'O' in various contexts

No Comments

No Known Activations