INDEX

Explanations

concepts related to data advertising and its sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

&E

-0.17

nds

-0.16

ieber

-0.15

vac

-0.15

POV

-0.15

ptime

-0.14

xab

-0.14

agua

-0.14

agne

-0.14

agma

-0.14

POSITIVE LOGITS

uste

0.17

ependency

0.15

uur

0.15

ropic

0.15

pu

0.14

enheim

0.14

oldem

0.14

brace

0.14

Activations Density 0.061%

concepts related to data advertising and its sources

No Comments

No Known Activations