INDEX

Explanations

references to specific time periods, events, and collaborations

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

Ð²Ð°Ð¹

-0.16

hai

-0.15

holm

-0.15

esco

-0.14

çĦ¶

-0.14

 newsp

-0.14

blem

-0.14

 ØŃØ§ÙĦ

-0.14

icio

-0.13

uely

-0.13

POSITIVE LOGITS

Flush

0.16

maz

0.15

ingroup

0.15

0.14

tt

0.14

 Quá»ĳc

0.14

anche

0.14

upp

0.13

itches

0.13

Activations Density 0.112%

references to specific time periods, events, and collaborations

No Comments

No Known Activations