INDEX

Explanations

terminology related to risk and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 náº¡n

-0.15

éĢł

-0.15

clamp

-0.15

 Bender

-0.15

CALE

-0.15

ÛĮÚ©ÛĮ

-0.15

undra

-0.14

ulton

-0.14

vr

-0.14

POSITIVE LOGITS

lessly

0.17

owitz

0.16

 hÃ£

0.16

DAC

0.15

íħĶ

0.15

ãģ¦

0.15

mong

0.15

à±

0.14

ron

0.14

rist

0.14

Activations Density 0.024%

terminology related to risk and its implications

No Comments

No Known Activations