INDEX

Explanations

instances of memory and recollection

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

leta

-0.17

Zem

-0.17

hÃ¡

-0.15

osen

-0.15

oppel

-0.14

 Chick

-0.14

eping

-0.14

ãĤ¹ãĥĨ

-0.14

.mvc

-0.14

abet

-0.13

POSITIVE LOGITS

omik

0.17

:inline

0.16

ãĥ«ãĤ¯

0.15

arger

0.15

kie

0.14

ylon

0.14

ariat

0.14

 conf

0.13

 Proceed

0.13

æĨ¶

0.13

Activations Density 0.020%

instances of memory and recollection

No Comments

No Known Activations