INDEX

Explanations

references to work and employment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

eno

-0.15

 Carnegie

-0.15

ues

-0.14

egend

-0.14

ussy

-0.14

snap

-0.14

_DLL

-0.14

æŃ

-0.14

GetProperty

-0.13

 alone

-0.13

POSITIVE LOGITS

Ã¶s

0.19

ÐºÐ°Ð²

0.15

allis

0.14

pcf

0.14

 petition

0.14

omik

0.14

Ð»ÐµÑĢÐ³

0.14

 Purple

0.14

olor

0.13

VOKE

0.13

Activations Density 0.002%

references to work and employment

No Comments

No Known Activations