INDEX

Explanations

technical terms and coding-related language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ulty

-0.18

èĬ

-0.16

alf

-0.15

 Array

-0.15

 Trou

-0.14

 Cone

-0.14

ãģĵãģĿ

-0.14

byn

-0.14

 cÃ´t

-0.14

POSITIVE LOGITS

'gc

0.19

ugin

0.18

asje

0.16

UGIN

0.16

.Mobile

0.16

 optarg

0.15

ADATA

0.15

yÅ¡

0.15

>Main

0.15

IVATE

0.15

Activations Density 0.096%

technical terms and coding-related language

No Comments

No Known Activations