INDEX

Explanations

references to specific statistical data or citations in scholarly contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 http

-0.18

http

-0.15

](

-0.15

rox

-0.15

https

-0.15

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

-0.15

:http

-0.14

çĳŁ

-0.14

tex

-0.14

 https

-0.14

POSITIVE LOGITS

Â£Â£

0.15

strup

0.15

Ø¹Ø¯Ø§Ø¯

0.15

orio

0.14

:"-"`↵

0.13

stras

0.13

eny

0.13

rary

0.13

ncoder

0.13

/channel

0.13

Activations Density 0.156%

references to specific statistical data or citations in scholarly contexts

No Comments

No Known Activations