INDEX

Explanations

references to radio broadcasts or related media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 cave

-0.15

 ÑģÐ¿Ð¸Ñģ

-0.15

ner

-0.15

ments

-0.14

uru

-0.14

nea

-0.14

NESS

-0.14

mentation

-0.14

ment

-0.13

 table

-0.13

POSITIVE LOGITS

anford

0.19

ÑıÐ±

0.16

akter

0.15

esium

0.15

 wings

0.14

indre

0.14

arse

0.14

 Dickinson

0.14

PFN

0.14

 authDomain

0.14

Activations Density 0.010%

references to radio broadcasts or related media

No Comments

No Known Activations