INDEX

Explanations

technical terminology related to software or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

onders

-0.15

hti

-0.14

esso

-0.14

_MAXIMUM

-0.14

azu

-0.14

 VÃ¡c

-0.13

à¹Ĥà¸Ļ

-0.13

aju

-0.13

 Slut

-0.13

wise

-0.13

POSITIVE LOGITS

_iters

0.14

.arm

0.13

lech

0.13

olicit

0.13

DataService

0.12

scape

0.12

 GURL

0.12

It

0.12

Bil

0.12

ussen

0.12

Activations Density 0.040%

technical terminology related to software or programming concepts

No Comments

No Known Activations