INDEX

Explanations

specific terms related to programming or system implementation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Kok

-0.15

jang

-0.15

 cruc

-0.14

Eis

-0.14

wr

-0.14

 paras

-0.14

 ÑĤÑĢÑĥ

-0.13

 Admir

-0.13

 buck

-0.13

POSITIVE LOGITS

vae

0.16

 trá»Ŀi

0.16

arde

0.15

elper

0.15

iday

0.14

ridged

0.14

à¹Ħà¸Ĥ

0.14

urch

0.14

åĢ

0.14

ean

0.14

Activations Density 0.004%

specific terms related to programming or system implementation

No Comments

No Known Activations