INDEX

Explanations

references to specific years, particularly from the 2000s

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

izik

-0.17

acob

-0.17

riger

-0.15

ë¦Ħ

-0.15

Ø§Ø¦Ø²

-0.14

 Instruments

-0.14

Hol

-0.14

 Instrument

-0.14

ented

-0.14

ondo

-0.14

POSITIVE LOGITS

kdir

0.16

ths

0.15

ãĥ«ãĥĪ

0.15

-aff

0.14

æĶ¯

0.14

utc

0.13

æ®Ĭ

0.13

mesh

0.13

FLT

0.13

frauen

0.13

Activations Density 0.078%

references to specific years, particularly from the 2000s

No Comments

No Known Activations