INDEX

Explanations

references to positions, roles, and significant projects or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 wherever

-0.20

-0.15

positor

-0.15

agua

-0.15

rens

-0.15

Localized

-0.15

ëĿ½

-0.14

aney

-0.14

elist

-0.14

 prolong

-0.14

POSITIVE LOGITS

 filled

0.25

 full

0.24

 containing

0.23

 attended

0.21

 despite

0.21

 FULL

0.20

 featuring

0.20

 trotz

0.20

 llen

0.20

noch

0.19

Activations Density 0.031%

references to positions, roles, and significant projects or events

No Comments

No Known Activations