INDEX

Explanations

references to TV show plot details and character developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.opensource

-0.17

rai

-0.15

azo

-0.15

hurst

-0.15

 apart

-0.15

ELS

-0.15

prite

-0.15

boro

-0.14

inton

-0.14

°

-0.14

POSITIVE LOGITS

à¸į

0.16

0.15

.cv

0.15

uttle

0.14

amped

0.14

aad

0.14

uche

0.14

 à¤ªà¤¦

0.13

prompt

0.13

Activations Density 0.171%

references to TV show plot details and character developments

No Comments

No Known Activations