INDEX

Explanations

key phrases related to television programming and production metrics

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

çĿ£

-0.15

 Markup

-0.15

ampa

-0.15

mits

-0.15

mouseenter

-0.15

æīĺ

-0.14

 extinct

-0.14

aux

-0.14

imax

-0.14

 Toll

-0.14

POSITIVE LOGITS

hausen

0.17

ugen

0.15

OF

0.15

 zoekt

0.15

oven

0.14

 Harvey

0.14

eras

0.14

ervals

0.14

lical

0.14

Activations Density 0.004%

key phrases related to television programming and production metrics

No Comments

No Known Activations