INDEX

Explanations

punctuation marks, specifically semicolons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

er

-0.21

-0.19

eres

-0.16

-0.15

 insign

-0.15

opes

-0.15

Ø§

-0.15

gig

-0.15

↵

-0.15

POSITIVE LOGITS

fillType

0.17

 FindObjectOfType

0.16

 ActiveForm

0.16

koli

0.15

ì¼ĵ

0.15

ErrorException

0.14

Ø¡

0.14

ormap

0.14

ugi

0.14

asurer

0.14

Activations Density 0.055%

punctuation marks, specifically semicolons

No Comments

No Known Activations