INDEX

Explanations

terms and phrases related to ugliness or negative appearances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Circular

-0.15

 gent

-0.15

Ð²Ñĭ

-0.15

Curve

-0.14

ected

-0.14

à¤¨à¤²

-0.14

 Reserved

-0.14

é

-0.14

Ø§ÙĦÙĩ

-0.14

uzz

-0.13

POSITIVE LOGITS

 enough

0.17

ufac

0.16

shan

0.15

ontent

0.15

 precisely

0.15

stein

0.15

sak

0.14

leme

0.14

 Byrne

0.14

acha

0.14

Activations Density 0.011%

terms and phrases related to ugliness or negative appearances

No Comments

No Known Activations