INDEX

Explanations

instances of the word "plug" and related terms 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

olver

-0.15

ï¸ı

-0.15

ÑĢÑĥÐ´

-0.15

anou

-0.14

FX

-0.14

OCUMENT

-0.14

å¿µ

-0.13

 Gingrich

-0.13

rene

-0.13

opsis

-0.13

POSITIVE LOGITS

erties

0.17

adoo

0.16

Hed

0.15

placeholders

0.15

ovic

0.15

ÐµÐ»Ð¾Ð²

0.15

edReader

0.14

emo

0.14

Pri

0.14

Ð¡Ðł

0.14

Activations Density 0.009%

instances of the word "plug" and related terms in various contexts

No Comments

No Known Activations