INDEX

Explanations

occupations and job titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ask

-0.15

ader

-0.15

oston

-0.14

vard

-0.14

atak

-0.14

rex

-0.14

gg

-0.14

igm

-0.13

stad

-0.13

POSITIVE LOGITS

.camel

0.15

HttpException

0.15

URAL

0.15

 Ð¾Ð±ÑĢÐ°Ð·Ð¾Ð¼

0.13

ãĤ¯ãĥ©ãĥĸ

0.13

å«Į

0.13

ural

0.13

inp

0.13

)test

0.13

 æĪ

0.13

Activations Density 0.051%

occupations and job titles

No Comments

No Known Activations