INDEX

Explanations

technical terms related to engineering and home improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ustil

-0.19

vig

-0.17

ouden

-0.16

ç§

-0.15

áº£o

-0.15

.simps

-0.14

æĸĹ

-0.14

èĶµ

-0.14

ãĥ¼ãĤ¯

-0.14

etc

-0.14

POSITIVE LOGITS

alue

0.14

 desn

0.14

abe

0.13

PFN

0.13

 Donovan

0.13

RG

0.13

aire

0.13

Activations Density 0.001%

technical terms related to engineering and home improvement

No Comments

No Known Activations