INDEX

Explanations

specific locations and addresses

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

orks

-0.17

 infl

-0.17

quete

-0.15

 extrapol

-0.15

uentes

-0.15

usa

-0.15

anka

-0.14

lant

-0.14

 Meadows

-0.14

 intr

-0.14

POSITIVE LOGITS

 Broadway

0.19

 Main

0.19

 Vine

0.18

Broad

0.18

 Sixth

0.18

 Market

0.17

 Seventh

0.17

rush

0.17

 Fifth

0.17

 Walnut

0.16

Activations Density 0.127%

specific locations and addresses

No Comments

No Known Activations