INDEX

Explanations

terms related to disability and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

omo

-0.16

insky

-0.16

 lÃłnh

-0.15

à¸µà¹Ģà¸Ķ

-0.15

å¸ģ

-0.15

indir

-0.14

healthy

-0.14

aco

-0.14

.localization

-0.14

ira

-0.14

POSITIVE LOGITS

/dis

0.22

 rights

0.17

-rights

0.16

-adjust

0.16

 Rights

0.16

owned

0.16

 spectrum

0.16

iston

0.15

 parking

0.15

 pride

0.15

Activations Density 0.019%

terms related to disability and its implications

No Comments

No Known Activations