INDEX

Explanations

references to time periods and changes over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

yet

-0.21

yet

-0.19

due

-0.19

Yet

-0.18

due

-0.18

ERM

-0.17

Yet

-0.16

eya

-0.16

anie

-0.15

 compared

-0.15

POSITIVE LOGITS

 though

0.29

 however

0.28

though

0.21

Though

0.20

 Though

0.19

 denn

0.19

 because

0.18

 aber

0.18

however

0.18

Because

0.17

Activations Density 0.022%

references to time periods and changes over time

No Comments

No Known Activations