INDEX

Explanations

terms related to technical specifications or components, particularly in a programming or engineering context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

adesh

-0.16

anton

-0.16

 scar

-0.16

ellen

-0.16

-0.15

-0.14

 Scar

-0.14

pdf

-0.14

POSITIVE LOGITS

Kah

0.17

ambre

0.16

¾

0.16

ìĪľ

0.15

Frank

0.15

erp

0.14

lob

0.14

lotte

0.14

rowsable

0.14

aub

0.14

Activations Density 0.024%

terms related to technical specifications or components, particularly in a programming or engineering context

No Comments

No Known Activations