INDEX

Explanations

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aget

-0.17

allo

-0.15

atts

-0.15

ï¼

-0.14

åĳĪ

-0.14

ickets

-0.14

esta

-0.14

olumn

-0.14

isay

-0.14

puty

-0.14

POSITIVE LOGITS

íĥ

0.15

ìį¨

0.15

èģĶç³»

0.14

lem

0.14

 ASTM

0.14

 ÑĢÐ°ÑģÑĩ

0.13

 Interr

0.13

Lik

0.13

 invers

0.13

py

0.13

Activations Density 0.079%

proper nouns, specifically names of people and organizations

No Comments

No Known Activations