INDEX

Explanations

procedural steps and instructions related to technical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

AGMA

-0.14

olvable

-0.14

que

-0.14

esting

-0.14

Ä©

-0.14

afs

-0.14

>Note

-0.13

Ã³mo

-0.13

lew

-0.13

POSITIVE LOGITS

dden

0.15

ï¸ı

0.15

NavController

0.15

íģ¼

0.14

èĢĮ

0.14

andan

0.14

ContentSize

0.14

 Garn

0.13

edException

0.13

etwork

0.13

Activations Density 0.046%

procedural steps and instructions related to technical processes

No Comments

No Known Activations