INDEX

Explanations

terms related to boundaries and enclosures in property contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Bust

-0.17

clr

-0.15

wiki

-0.15

 Seks

-0.14

 bust

-0.14

pled

-0.14

åı·

-0.14

.fun

-0.14

aska

-0.14

 Carpenter

-0.14

POSITIVE LOGITS

åł´

0.17

 fence

0.16

 fences

0.16

antan

0.15

Ð¾Ð½ÑĮ

0.15

 é©

0.14

Ø±ÙĪØ³

0.14

 Fence

0.14

 Barbar

0.14

 barbecue

0.14

Activations Density 0.043%

terms related to boundaries and enclosures in property contexts

No Comments

No Known Activations