INDEX

Explanations

words related to connections and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

sworth

-0.15

umbo

-0.14

deer

-0.14

("'"

-0.14

/UIKit

-0.13

loor

-0.13

fod

-0.13

ÑĬ

-0.13

_mirror

-0.13

TRS

-0.13

POSITIVE LOGITS

lif

0.15

alis

0.15

ally

0.14

ity

0.14

erate

0.14

 Honest

0.14

Ã§Ä±

0.13

 Linh

0.13

Lif

0.13

ill

0.13

Activations Density 1.615%

words related to connections and relationships

No Comments

No Known Activations