INDEX

Explanations

occurrences of the abbreviation "DC" in various contexts

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

Pod

-0.16

ookies

-0.15

folk

-0.14

onaut

-0.14

 Birch

-0.14

ook

-0.14

isen

-0.13

ç¸

-0.13

ledge

-0.13

Ã¸j

-0.13

POSITIVE LOGITS

zens

0.15

 Toll

0.14

ê´

0.14

zs

0.14

 Wanna

0.14

indir

0.14

ickey

0.14

 Wahl

0.13

oz

0.13

pts

0.13

Activations Density 0.021%

occurrences of the abbreviation "DC" in various contexts

No Comments

No Known Activations