INDEX

Explanations

phrases that indicate inclusion or reference specific examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

adil

-0.15

ÑĢÐ°ÑīÐµÐ½Ð¸Ñı

-0.14

remen

-0.14

inch

-0.14

anca

-0.14

inia

-0.14

¹

-0.14

æ¥½ãģĹ

-0.14

iphers

-0.14

ramer

-0.13

POSITIVE LOGITS

 ones

0.18

 Coff

0.15

tility

0.14

.bpm

0.14

URN

0.14

ruba

0.14

efa

0.14

maal

0.13

ÃŃl

0.13

udas

0.13

Activations Density 0.098%

phrases that indicate inclusion or reference specific examples

No Comments

No Known Activations