INDEX

Explanations

significant numerical values or measurements related to objects and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

terra

-0.17

 SaÄŁ

-0.14

 Antar

-0.14

ç¨¿

-0.14

 SayÄ±

-0.13

detach

-0.13

ourke

-0.13

 Delegate

-0.13

èīĩ

-0.13

POSITIVE LOGITS

nze

0.15

omite

0.15

aname

0.14

áº¥u

0.14

fout

0.14

ighth

0.14

omic

0.14

_FM

0.14

 Wings

0.13

lÃ¡

0.13

Activations Density 0.399%

significant numerical values or measurements related to objects and events

No Comments

No Known Activations