INDEX

Explanations

mentions of "Pacific" or related geographical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

owell

-0.15

 pais

-0.15

 Threshold

-0.15

 ì½

-0.15

ilon

-0.14

elier

-0.14

nej

-0.14

 Monte

-0.14

terraform

-0.14

Ã¥r

-0.14

POSITIVE LOGITS

Rim

0.29

ally

0.24

0.21

ific

0.20

rim

0.20

rim

0.20

IFIC

0.19

 Ocean

0.19

 Coast

0.18

rones

0.18

Activations Density 0.010%

mentions of "Pacific" or related geographical terms

No Comments

No Known Activations