INDEX

Explanations

references to casual or informal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

à¤¤à¤®

-0.16

eah

-0.15

eil

-0.15

ÃŃc

-0.15

ente

-0.14

ÑĩÐ°

-0.14

ENTE

-0.14

ppard

-0.14

orman

-0.14

imbledon

-0.14

POSITIVE LOGITS

ual

0.27

imir

0.23

anova

0.22

ually

0.22

uality

0.21

andra

0.20

beer

0.19

ino

0.19

uar

0.19

aub

0.18

Activations Density 0.017%

references to casual or informal contexts

No Comments

No Known Activations