INDEX

Explanations

references to language standards and their variations

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

ument

-0.16

bit

-0.16

atar

-0.15

-Clause

-0.15

ham

-0.15

 nursing

-0.15

azi

-0.15

ogan

-0.14

)NULL

-0.14

Apt

-0.14

POSITIVE LOGITS

/pop

0.19

 trends

0.16

exp

0.16

ÑĥÑĢÐ°

0.15

 popular

0.15

popular

0.15

enser

0.15

 Interior

0.15

arry

0.14

aban

0.14

Activations Density 0.262%

references to language standards and their variations

No Comments

No Known Activations