INDEX

Explanations

variations of the word "unleash."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

imension

-0.18

imson

-0.15

.au

-0.15

okt

-0.14

senal

-0.14

lifetime

-0.14

Lite

-0.14

gers

-0.14

 Franken

-0.14

jsc

-0.14

POSITIVE LOGITS

ivel

0.16

0.15

.tem

0.15

ered

0.15

rod

0.14

 costly

0.14

umatic

0.14

ac

0.14

 Pear

0.14

emble

0.14

Activations Density 0.002%

variations of the word "unleash."

No Comments

No Known Activations