INDEX

Explanations

specific names and affiliations of individuals likely related to academic or scientific contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ENSE

-0.15

cano

-0.15

§è¡Į

-0.14

oft

-0.14

vana

-0.14

 Î³Îµ

-0.13

emento

-0.13

 Ø¨Ø¹

-0.13

SError

-0.13

Bs

-0.13

POSITIVE LOGITS

ÑĢÑĥÐ½

0.16

iolet

0.15

awn

0.15

æª

0.14

ìŀĲìĿ¸

0.14

ÑĥÐ¶Ð´

0.14

Maz

0.13

.Rendering

0.13

ajs

0.13

Activations Density 0.025%

specific names and affiliations of individuals likely related to academic or scientific contributions

No Comments

No Known Activations