INDEX

Explanations

descriptive phrases introducing people, objects, or concepts in a positive manner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

alion

-0.17

alars

-0.15

okable

-0.14

AGR

-0.14

anean

-0.13

bot

-0.13

cob

-0.13

geist

-0.13

 goodness

-0.13

ê·Ģ

-0.13

POSITIVE LOGITS

 ticking

0.15

 Pist

0.15

ÎºÎ±Î½

0.14

 ÄĳÃ´i

0.14

 Benn

0.13

ipe

0.13

 Powell

0.13

esson

0.13

xa

0.13

ONSE

0.13

Activations Density 0.088%

descriptive phrases introducing people, objects, or concepts in a positive manner

No Comments

No Known Activations