INDEX

Explanations

conditional phrases that suggest potential actions or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

arge

-0.15

gal

-0.15

otal

-0.14

gun

-0.14

leta

-0.14

ety

-0.14

ella

-0.14

ego

-0.14

ropri

-0.14

 Inner

-0.14

POSITIVE LOGITS

iliz

0.15

Fx

0.15

jav

0.14

ÛĮØ¯ÙĨ

0.14

 ìĿ´ëĬĶ

0.14

alet

0.14

lac

0.13

 ÙħØ§Ø¯

0.13

Activations Density 0.020%

conditional phrases that suggest potential actions or outcomes

No Comments

No Known Activations