INDEX

Explanations

references to fields and areas of study or expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

enth

-0.14

omp

-0.14

odian

-0.14

Ð¾Ð´Ð°Ð²

-0.14

arde

-0.13

ampa

-0.13

intendent

-0.13

alls

-0.13

 Multip

-0.13

immer

-0.13

POSITIVE LOGITS

 field

0.24

 areas

0.21

 fields

0.21

 getField

0.20

field

0.20

é¢ĨåŁŁ

0.19

-field

0.18

(field

0.18

_field

0.18

[field

0.18

Activations Density 0.047%

references to fields and areas of study or expertise

No Comments

No Known Activations