INDEX

Explanations

words and phrases associated with television programming and education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.16

ovation

-0.14

.StoredProcedure

-0.14

 empire

-0.13

Å¡ti

-0.13

ãĥĲãĥ¼

-0.13

ryn

-0.13

 rozs

-0.13

à¸ªà¸Ķ

-0.13

POSITIVE LOGITS

xes

0.16

oble

0.16

inha

0.15

 solic

0.15

chen

0.15

ets

0.14

 slack

0.14

emen

0.14

imu

0.14

 Pompe

0.13

Activations Density 0.010%

words and phrases associated with television programming and education

No Comments

No Known Activations