INDEX

Explanations

website-related terminology and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uges

-0.16

ÙĪÙĬÙĥ

-0.16

.failure

-0.15

ault

-0.15

uum

-0.14

olm

-0.14

auge

-0.13

ear

-0.13

afari

-0.13

Ear

-0.13

POSITIVE LOGITS

 Ø±Ø³ÙħÛĮ

0.16

 oficial

0.15

ovatel

0.14

onet

0.14

athy

0.14

 isEnabled

0.14

assing

0.13

ASF

0.13

ilter

0.13

stan

0.13

Activations Density 0.032%

website-related terminology and references

No Comments

No Known Activations