INDEX

Explanations

terms related to governmental restrictions and legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

plusplus

-0.14

 sembl

-0.14

mention

-0.14

hsi

-0.14

oby

-0.13

IBUTES

-0.13

 geÃ§en

-0.12

 textu

-0.12

aal

-0.12

 nouvel

-0.12

POSITIVE LOGITS

 could

0.23

 finally

0.21

ang

0.19

 likely

0.19

hal

0.19

may

0.18

 expected

0.18

not

0.17

 still

0.17

Activations Density 0.213%

terms related to governmental restrictions and legal issues

No Comments

No Known Activations