INDEX

Explanations

numerical references or counts related to various subjects

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

è¬

-0.14

rang

-0.14

 anything

-0.14

oute

-0.14

iver

-0.14

 autorelease

-0.14

ÐºÑģÐ¿

-0.14

etta

-0.13

atta

-0.13

POSITIVE LOGITS

Pocket

0.17

ãĥªãĥ¼ãĤº

0.16

Ä©

0.15

ÑıÐ½

0.15

 Pocket

0.14

ãĥĵãĥ¼

0.14

 Faul

0.14

Åº

0.14

eric

0.14

-License

0.13

Activations Density 0.027%

numerical references or counts related to various subjects

No Comments

No Known Activations