INDEX

Explanations

structure and organization within academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

kinson

-0.17

isoft

-0.16

.extensions

-0.15

 Johnston

-0.15

/fw

-0.15

 Ø§ÙĦØ³ÙĦØ§Ùħ

-0.14

UGHT

-0.14

INES

-0.14

fd

-0.14

alle

-0.14

POSITIVE LOGITS

.Real

0.17

ennen

0.16

laden

0.16

 Ð³ÑĢÐµ

0.15

 jadx

0.15

RegularExpression

0.14

 fisse

0.14

âĹıâĹıâĹıâĹı

0.14

frauen

0.14

criptor

0.14

Activations Density 0.009%

structure and organization within academic papers

No Comments

No Known Activations