INDEX

Explanations

labels and markings on objects or packaging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

agra

-0.15

èįī

-0.15

à¸¹à¸¥

-0.15

isp

-0.14

osh

-0.14

ipo

-0.14

 Function

-0.14

osph

-0.14

enis

-0.13

Ð·ÑĮ

-0.13

POSITIVE LOGITS

ToObject

0.15

/Dk

0.14

oeff

0.14

unya

0.14

odus

0.14

 legion

0.14

 Sanford

0.14

.EndsWith

0.13

hevik

0.13

 Shard

0.13

Activations Density 0.072%

labels and markings on objects or packaging

No Comments

No Known Activations