INDEX

Explanations

elements related to literary analysis and thematic discussions

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

jezd

-0.17

kus

-0.16

 Daly

-0.16

ucs

-0.14

VIA

-0.13

praak

-0.13

 ÐºÐ¸ÑĢ

-0.13

undef

-0.13

league

-0.13

fort

-0.13

POSITIVE LOGITS

plot

0.17

 plot

0.16

bies

0.15

æ¤į

0.14

plots

0.14

 Plot

0.14

 plÃ¡

0.14

iker

0.14

Ep

0.14

DCF

0.13

Activations Density 0.241%

elements related to literary analysis and thematic discussions

No Comments

No Known Activations