INDEX

Explanations

terms related to selection and beneficiaries in a context of community involvement or project outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

á»ĩ

-0.18

nds

-0.15

conti

-0.15

ÑĩÐ¸Ðµ

-0.15

unta

-0.14

ialis

-0.14

íĶĪ

-0.14

ìĩ

-0.14

 stap

-0.14

eten

-0.14

POSITIVE LOGITS

 choice

0.17

 chosen

0.17

chosen

0.15

'gc

0.15

[Test

0.15

ered

0.15

choice

0.15

entials

0.14

 chose

0.14

cop

0.14

Activations Density 0.090%

terms related to selection and beneficiaries in a context of community involvement or project outcomes

No Comments

No Known Activations