INDEX

Explanations

specific linguistic elements from different languages or scripts, particularly related to terms or phrases that may be culturally or regionally significant

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ð

-0.15

å®ĺ

-0.15

ìľµ

-0.14

ÐµÐ³Ð¾ÑĢ

-0.14

eyh

-0.14

old

-0.14

Ð¾ÑģÐ½Ð¾Ð²

-0.14

lint

-0.13

oft

-0.13

Ù

-0.13

POSITIVE LOGITS

 pract

0.14

jeta

0.14

/topics

0.14

OCR

0.14

uler

0.13

ubber

0.13

Programming

0.13

linger

0.13

sembling

0.13

ivery

0.13

Activations Density 0.025%

specific linguistic elements from different languages or scripts, particularly related to terms or phrases that may be culturally or regionally significant

No Comments

No Known Activations