INDEX

Explanations

references to physical locations or movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Rapid

-0.16

ulta

-0.16

¸ı

-0.15

Ø´Ø§Ø±

-0.15

ood

-0.15

.recycle

-0.15

gart

-0.15

 undermin

-0.14

Ã¡le

-0.14

avia

-0.14

POSITIVE LOGITS

estone

0.16

atur

0.15

 vice

0.15

 Stamp

0.14

esson

0.14

imore

0.14

Ø§ÙģØª

0.14

gary

0.14

Tap

0.13

 Äĳá»ı

0.13

Activations Density 0.082%

references to physical locations or movements

No Comments

No Known Activations