INDEX

Explanations

words related to legal issues and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ABLE

-0.16

lessly

-0.15

ONEY

-0.15

ned

-0.14

borg

-0.13

 Truy

-0.13

linger

-0.13

izzare

-0.13

fax

-0.13

WithContext

-0.13

POSITIVE LOGITS

ils

0.17

entication

0.16

igo

0.15

il

0.15

us

0.15

 dá»±ng

0.14

ãĤ·ãĥ¼

0.14

ya

0.14

ine

0.14

als

0.14

Activations Density 0.634%

words related to legal issues and governance

No Comments

No Known Activations