INDEX

Explanations

references to socioeconomic classes and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

åĬ¨

-0.15

æİĽ

-0.15

/customer

-0.15

llen

-0.14

enti

-0.14

åĭķ

-0.14

£i

-0.14

ajo

-0.14

ollo

-0.14

ensa

-0.14

POSITIVE LOGITS

gers

0.19

0.16

éĸĵ

0.15

eld

0.15

alan

0.15

æĨ

0.14

anime

0.14

oles

0.14

elts

0.14

RAW

0.14

Activations Density 0.018%

references to socioeconomic classes and their characteristics

No Comments

No Known Activations