INDEX

Explanations

phrases indicating additional quantity or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

peg

-0.14

prop

-0.14

oshi

-0.14

coon

-0.14

aklÄ±

-0.13

iram

-0.13

maktan

-0.13

base

-0.13

 tread

-0.13

victim

-0.13

POSITIVE LOGITS

(extra

0.23

 extra

0.23

-extra

0.23

 added

0.20

 EXTRA

0.20

extra

0.20

/add

0.20

 Added

0.19

-added

0.19

/new

0.17

Activations Density 0.169%

phrases indicating additional quantity or items

No Comments

No Known Activations