INDEX

Explanations

references to follow-up actions and their impacts on various aspects of a discussion or plan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Affected

-0.16

illet

-0.15

-0.14

ãĥ³ãĤ¹

-0.14

à¸²à¸°

-0.14

ippet

-0.14

ERÄ°

-0.14

affer

-0.14

 MISS

-0.14

urtles

-0.13

POSITIVE LOGITS

 secondary

0.17

/add

0.16

oser

0.15

secondary

0.15

OSP

0.15

é¡¹

0.14

 Baxter

0.14

 Doyle

0.14

ead

0.14

Activations Density 0.196%

references to follow-up actions and their impacts on various aspects of a discussion or plan

No Comments

No Known Activations