INDEX

Explanations

phrases that express interest or curiosity about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

cion

-0.16

hem

-0.15

stk

-0.14

laz

-0.14

Prev

-0.14

orpion

-0.14

isons

-0.14

PLE

-0.14

agle

-0.14

å¹¹ç·ļ

-0.14

POSITIVE LOGITS

mint

0.17

 interest

0.15

wend

0.15

 Ø¯ÙĨØ¨Ø§ÙĦ

0.15

ToShow

0.14

wang

0.14

ryn

0.13

ãĥĬãĥ¼

0.13

 interested

0.13

 whether

0.13

Activations Density 0.059%

phrases that express interest or curiosity about various topics

No Comments

No Known Activations