INDEX

Explanations

proper nouns and significant names related to individuals 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

rsp

-0.17

LOPT

-0.17

earer

-0.14

anford

-0.14

lsx

-0.14

Ã½n

-0.14

kart

-0.14

ADOS

-0.14

thead

-0.14

ONS

-0.14

POSITIVE LOGITS

ulu

0.19

Mp

0.15

âīł

0.15

manuel

0.15

abwe

0.15

vw

0.14

 Nigerian

0.14

Vue

0.14

amb

0.14

wa

0.14

Activations Density 0.132%

proper nouns and significant names related to individuals and organizations

No Comments

No Known Activations