INDEX

Explanations

irrelevant or non-informative text, likely due to encoding issues or noise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.19

-0.18

exp

-0.18

pos

-0.17

bis

-0.17

-0.16

av

-0.16

POSITIVE LOGITS

 addCriterion

0.17

 Ð¼ÐµÑĤÐ°Ð»Ð»Ð¸

0.17

adÄ±k

0.16

Äĩe

0.16

reesome

0.16

isContained

0.15

.IContainer

0.15

 diseÃ±ador

0.15

Â°Ð¡

0.15

jedn

0.15

Activations Density 0.017%

irrelevant or non-informative text, likely due to encoding issues or noise

No Comments

No Known Activations