INDEX

Explanations

mentions of "Doctor Who."

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

ETCH

-0.17

inja

-0.15

ijd

-0.15

inear

-0.15

eye

-0.15

ugg

-0.14

isan

-0.14

åĬŁ

-0.14

lander

-0.14

 exit

-0.13

POSITIVE LOGITS

 knot

0.16

imar

0.16

-alert

0.15

 Maritime

0.15

à¸¢à¸§

0.15

Ø¢Ùħ

0.14

redient

0.14

leton

0.14

alert

0.14

ÙĦÛĮØ³ÛĮ

0.14

Activations Density 0.023%

mentions of "Doctor Who."

No Comments

No Known Activations