INDEX

Explanations

references to authors and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

azzo

-0.17

eczy

-0.15

ileo

-0.15

ossa

-0.15

 Linh

-0.14

ozor

-0.14

ãĥĿãĥ¼ãĥĪ

-0.14

elsing

-0.14

Prov

-0.13

POSITIVE LOGITS

Pac

0.28

 Nach

0.25

 Jord

0.24

Tx

0.24

Tx

0.22

Ign

0.22

 Germ

0.22

Pep

0.21

 Jesus

0.21

 Angeles

0.21

Activations Density 0.021%

references to authors and literary works

No Comments

No Known Activations