INDEX

Explanations

punctuation marks, particularly commas and question marks, indicating dialogue or shifts in thought

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

 Cecil

-0.17

uce

-0.16

ugg

-0.16

orny

-0.15

ASON

-0.15

worthy

-0.15

aling

-0.15

igy

-0.15

cken

-0.14

buquerque

-0.14

POSITIVE LOGITS

astes

0.16

tent

0.15

anst

0.14

taÅŁ

0.14

illis

0.14

prak

0.14

ilis

0.14

ÏģÎ·

0.14

 Swords

0.13

uis

0.13

Activations Density 0.038%

punctuation marks, particularly commas and question marks, indicating dialogue or shifts in thought

No Comments

No Known Activations