INDEX

Explanations

terms related to user-friendliness and digital content management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

addock

-0.17

olen

-0.16

patrick

-0.16

umen

-0.15

eker

-0.15

 Shades

-0.14

tight

-0.14

SCP

-0.13

icken

-0.13

 Hazard

-0.13

POSITIVE LOGITS

eme

0.15

ãĥ¼ãĥª

0.14

eria

0.14

.githubusercontent

0.14

edir

0.14

 Atmos

0.14

0.13

ids

0.13

 somehow

0.13

Activations Density 0.038%

terms related to user-friendliness and digital content management

No Comments

No Known Activations