INDEX

Explanations

phrases indicating statements or remarks made by individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lyn

-0.14

 somebody

-0.14

 someone

-0.14

 either

-0.14

ahi

-0.14

ãĥ¼ãĥ³

-0.13

Ãªu

-0.13

 itself

-0.13

Rou

-0.13

 anybody

-0.13

POSITIVE LOGITS

 prepared

0.28

prepared

0.23

 Prepared

0.21

 remarks

0.17

 reference

0.17

 comentarios

0.15

 tones

0.15

 emailed

0.15

 referencia

0.15

reference

0.15

Activations Density 0.021%

phrases indicating statements or remarks made by individuals

No Comments

No Known Activations