INDEX

Explanations

terms related to vision impairment or blindness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erp

-0.16

åĪ¶

-0.15

alian

-0.15

ë¯¼

-0.15

-0.14

eel

-0.14

cher

-0.14

áº¥n

-0.14

à¸ªà¸°

-0.14

 Meer

-0.13

POSITIVE LOGITS

 blind

0.67

blind

0.61

 Blind

0.60

 deaf

0.59

-blind

0.58

 blindness

0.57

 blinded

0.38

 blinds

0.36

 Ð³Ð»Ñĥ

0.35

 hearing

0.32

Activations Density 0.063%

terms related to vision impairment or blindness

No Comments

No Known Activations