INDEX

Explanations

expressions that indicate differing perspectives or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lagen

-0.15

obar

-0.14

puter

-0.14

ä»£

-0.14

AndPassword

-0.14

-circle

-0.14

 circle

-0.14

ISMATCH

-0.14

cheon

-0.14

ucci

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.16

ersh

0.16

agal

0.15

CCA

0.15

elop

0.14

 intf

0.14

 Haven

0.14

ë¯

0.14

terr

0.14

Activations Density 0.002%

expressions that indicate differing perspectives or experiences

No Comments

No Known Activations