INDEX

Explanations

references to locations and travel destinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

razil

-0.15

Î¸Ïħ

-0.15

hek

-0.15

 æ¢

-0.14

brew

-0.14

Ngb

-0.14

 stat

-0.14

 cargo

-0.14

currentColor

-0.14

-counter

-0.14

POSITIVE LOGITS

Tor

0.25

 Play

0.25

 Costa

0.23

Fu

0.23

Ben

0.22

 Sierra

0.21

 Golf

0.21

 Alman

0.21

Play

0.21

Tor

0.20

Activations Density 0.021%

references to locations and travel destinations

No Comments

No Known Activations