INDEX

Explanations

terms related to product features and offerings

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

iant

-0.16

orges

-0.15

iams

-0.15

noinspection

-0.14

untos

-0.14

ãĥ£

-0.14

uth

-0.14

iants

-0.14

izer

-0.13

 latex

-0.13

POSITIVE LOGITS

ÃŁ

0.17

zik

0.15

idir

0.15

DeltaTime

0.15

ventions

0.15

lish

0.14

seau

0.14

 bumps

0.14

ãģ£ãģ¡

0.13

ande

0.13

Activations Density 0.206%

terms related to product features and offerings

No Comments

No Known Activations