INDEX

Explanations

instances of the word "this" and related phrases indicating significance or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 ones

-0.16

ãĥ¼ãĥ¬

-0.16

 conf

-0.15

 disposable

-0.15

ria

-0.15

æĢ

-0.14

infer

-0.14

 other

-0.14

iddle

-0.14

POSITIVE LOGITS

 initiative

0.17

evenodd

0.16

eldorf

0.15

move

0.15

 move

0.15

opak

0.14

ÑĨÐµÐ½ÑĤÑĢÐ°

0.14

 opportunity

0.14

urma

0.14

 gesture

0.14

Activations Density 0.111%

instances of the word "this" and related phrases indicating significance or importance

No Comments

No Known Activations