INDEX

Explanations

numerical values and metrics related to funding, viewership, and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Glover

-0.16

immel

-0.15

ater

-0.15

ister

-0.14

smo

-0.14

ense

-0.14

 bible

-0.13

ijo

-0.13

ritten

-0.13

POSITIVE LOGITS

íĻĪ

0.15

obra

0.15

âĹİ

0.14

Ã½Å¡

0.14

 Serif

0.14

enticate

0.13

.paging

0.13

 Pied

0.13

RequestBody

0.13

buz

0.13

Activations Density 0.525%

numerical values and metrics related to funding, viewership, and statistical data

No Comments

No Known Activations