INDEX

Explanations

punctuation marks and query-like constructs indicating uncertainty or questioning tone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

kr

-0.15

ability

-0.15

inge

-0.14

 enacted

-0.14

activity

-0.13

/v

-0.13

Ã©e

-0.13

 interv

-0.13

rv

-0.13

heart

-0.13

POSITIVE LOGITS

à¸±à¸¢

0.15

|_|

0.15

FormatException

0.15

 Guth

0.15

âĶĺ

0.15

prec

0.15

angered

0.14

dol

0.14

inia

0.14

iture

0.14

Activations Density 0.049%

punctuation marks and query-like constructs indicating uncertainty or questioning tone

No Comments

No Known Activations