INDEX

Explanations

technical jargon and specific measurements related to scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rec

-0.14

 Barr

-0.14

.lp

-0.14

 Mehr

-0.13

mins

-0.13

 fucked

-0.13

alten

-0.13

Ö

-0.13

 fucks

-0.13

 Incontri

-0.13

POSITIVE LOGITS

-kind

0.16

-plan

0.16

Kind

0.16

serter

0.15

awe

0.15

-operator

0.15

.SIG

0.15

á»Ľp

0.14

iosa

0.14

 Kind

0.14

Activations Density 0.003%

technical jargon and specific measurements related to scientific or technical contexts

No Comments

No Known Activations