INDEX

Explanations

references to software programming concepts or terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Ð¿Ð¾Ð±Ð°

-0.20

rez

-0.18

ick

-0.16

Äįin

-0.14

 Ð½ÐµÐ³Ð¾

-0.14

 Ð½Ð¸Ñħ

-0.14

ãģĵãģ¨ãģ¯

-0.13

 Russo

-0.13

wald

-0.13

ARGS

-0.13

POSITIVE LOGITS

 Ð½Ð°

0.15

äºİ

0.15

LATED

0.15

Dag

0.15

 Dank

0.15

soon

0.15

0.14

irse

0.14

AAD

0.14

oad

0.14

Activations Density 0.076%

references to software programming concepts or terminology

No Comments

No Known Activations