INDEX

Explanations

specific terms and phrases related to actions and states of being, often in a legal or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 myself

-0.15

bject

-0.15

eka

-0.14

 Everybody

-0.14

à¸²à¸ĺ

-0.13

umont

-0.13

 Knock

-0.13

orf

-0.13

à¥įà¤¯à¤®

-0.13

egend

-0.13

POSITIVE LOGITS

someone

0.15

.dense

0.14

Soon

0.14

å»·

0.14

 somewhere

0.14

 someone

0.14

prech

0.13

ascar

0.13

 McGu

0.13

 alguien

0.13

Activations Density 0.039%

specific terms and phrases related to actions and states of being, often in a legal or formal context

No Comments

No Known Activations