INDEX

Explanations

expressions of understanding and realization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð¾ÑģÑĤ

-0.16

stub

-0.15

iyas

-0.15

CCR

-0.15

-0.14

auty

-0.14

Ð¼ÑĸÐ½Ñĸ

-0.14

oloji

-0.14

ignon

-0.14

ModelProperty

-0.14

POSITIVE LOGITS

anova

0.16

Tu

0.16

nowrap

0.15

rin

0.15

Î´ÎŃ

0.14

ryan

0.14

 unsub

0.14

Tu

0.14

jsonp

0.14

áº¡i

0.13

Activations Density 0.510%

expressions of understanding and realization

No Comments

No Known Activations