INDEX

Explanations

terms and phrases related to disabilities and disability rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ifen

-0.15

reira

-0.15

ertz

-0.15

Insensitive

-0.14

ENO

-0.14

zi

-0.14

ÙĪØ§ÙĦ

-0.14

avourites

-0.14

rei

-0.14

Ã¶l

-0.14

POSITIVE LOGITS

uous

0.15

ovich

0.15

unken

0.14

gn

0.14

ONTAL

0.14

Marsh

0.14

/disable

0.14

0.13

 pref

0.13

Activations Density 0.019%

terms and phrases related to disabilities and disability rights

No Comments

No Known Activations