INDEX

Explanations

terms and phrases related to negative characteristics and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 called

-0.14

apia

-0.14

XF

-0.13

Ð»ÑıÑħ

-0.13

aco

-0.13

Sl

-0.13

Dob

-0.13

POSITIVE LOGITS

 anything

0.18

STYPE

0.18

ä¸Ģç§į

0.17

omething

0.16

anything

0.16

 something

0.16

sembles

0.16

 gÃ¬

0.15

something

0.15

 trÃŃ

0.15

Activations Density 0.127%

terms and phrases related to negative characteristics and descriptions

No Comments

No Known Activations