INDEX

Explanations

expressions and phrases indicating approval or excitement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

bes

-0.18

czy

-0.15

atik

-0.15

larg

-0.14

aire

-0.14

inee

-0.14

Bes

-0.14

 simul

-0.14

ensor

-0.14

POSITIVE LOGITS

 stuff

0.20

icular

0.17

-looking

0.16

 things

0.16

cool

0.16

ÛĮÙĩ

0.15

assin

0.15

_stuff

0.15

 Stuff

0.15

/use

0.15

Activations Density 0.033%

expressions and phrases indicating approval or excitement

No Comments

No Known Activations