INDEX

Explanations

references to radio and its various formats and related terms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eds

-0.20

ments

-0.19

deaux

-0.18

ment

-0.15

ures

-0.15

ancer

-0.14

Fox

-0.14

inz

-0.14

FORMATION

-0.14

POSITIVE LOGITS

alnÄ±z

0.15

ëį°ìĿ´íĬ¸

0.15

dress

0.15

/books

0.15

iod

0.14

robat

0.14

_reserve

0.14

asset

0.14

mour

0.14

esium

0.14

Activations Density 0.018%

references to radio and its various formats and related terms

No Known Activations