INDEX

Explanations

dialogue tags and punctuation indicative of questioning or exclamation in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

issen

-0.15

anco

-0.15

igon

-0.14

lec

-0.14

ffen

-0.14

ael

-0.14

 alter

-0.14

enet

-0.14

/system

-0.14

velt

-0.14

POSITIVE LOGITS

Ã¸j

0.16

0.15

ackbar

0.15

brero

0.14

Ĥæķ°

0.14

encodeURIComponent

0.14

tras

0.14

ensing

0.14

_pd

0.13

Activations Density 0.098%

dialogue tags and punctuation indicative of questioning or exclamation in conversations

No Comments

No Known Activations