INDEX

Explanations

references to specific months and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ä¸ĥ

-0.24

-0.23

-0.22

 seventh

-0.21

 seven

-0.21

-seven

-0.20

 Seven

-0.19

 ä¸ĥ

-0.19

VII

-0.19

 sedm

-0.19

POSITIVE LOGITS

 five

0.24

 Five

0.24

 fifth

0.23

 äºĶ

0.21

five

0.21

 Fifth

0.21

äºĶæľĪ

0.20

à¥«

0.20

Activations Density 0.039%

references to specific months and dates

No Comments

No Known Activations