INDEX

Explanations

important nouns and verbs related to processes and actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

agi

-0.17

 Leon

-0.16

é»

-0.15

ÅĽnie

-0.15

-0.14

ike

-0.14

ystack

-0.14

aped

-0.14

OPY

-0.14

ledo

-0.14

POSITIVE LOGITS

YD

0.16

ollar

0.15

ìĸĳ

0.15

wald

0.14

 Hint

0.14

ÏĤ

0.13

 Progressive

0.13

dac

0.13

 progressive

0.13

ourcem

0.13

Activations Density 0.012%

important nouns and verbs related to processes and actions

No Comments

No Known Activations