INDEX

Explanations

technical terms and settings related to software configuration and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

sor

-0.15

igon

-0.15

Bow

-0.14

ska

-0.14

Ful

-0.14

 Freddie

-0.14

 Lens

-0.14

Ver

-0.14

 Sachs

-0.14

ilogy

-0.13

POSITIVE LOGITS

á»Ľt

0.16

orian

0.15

ithub

0.15

å¶

0.15

ëł

0.14

arak

0.14

azzi

0.14

æ´¾

0.14

ustos

0.14

Activations Density 0.293%

technical terms and settings related to software configuration and permissions

No Comments

No Known Activations