INDEX

Explanations

different types or categories of entities and concepts

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

orque

-0.16

inja

-0.16

Ø§ØªØ±

-0.16

ragment

-0.14

izu

-0.14

conde

-0.14

eve

-0.14

deen

-0.14

ÑĤÑĢÐ¸

-0.14

stm

-0.13

POSITIVE LOGITS

/type

0.18

/format

0.15

 type

0.15

 types

0.15

.Invoke

0.14

kiye

0.14

egend

0.14

tero

0.14

kol

0.14

(type

0.14

Activations Density 0.105%

different types or categories of entities and concepts

No Comments

No Known Activations