INDEX

Explanations

references to humor and comedic elements in the text

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

ormal

-0.17

rost

-0.16

heid

-0.15

adt

-0.15

bai

-0.15

ÑĨÐ¸Ð¿

-0.14

 Bers

-0.14

ouz

-0.14

umer

-0.14

Enlarge

-0.14

POSITIVE LOGITS

ifest

0.18

rung

0.16

CFO

0.16

fffffff

0.16

oft

0.14

prit

0.14

ÃŃch

0.14

 Rodney

0.14

 sapi

0.14

 Jarvis

0.14

Activations Density 0.013%

references to humor and comedic elements in the text

No Comments

No Known Activations