INDEX

Explanations

references to various locations or domains related to technology, data, and online environments

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

 surface

-0.15

agna

-0.15

ç»ı

-0.14

ÑĥÑĪÐºÐ°

-0.14

rost

-0.14

 Bite

-0.14

erule

-0.14

 Conditioning

-0.14

 suprem

-0.13

\Html

-0.13

POSITIVE LOGITS

ktor

0.17

ÐĲÑĢÑħÑĸÐ²

0.16

opic

0.14

iped

0.14

 Fear

0.14

#ad

0.13

.i

0.13

Hope

0.13

ÑĭÐ¿

0.13

Activations Density 0.558%

references to various locations or domains related to technology, data, and online environments

No Comments

No Known Activations