INDEX

Explanations

phrases related to legal claims and assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

emi

-0.17

Gee

-0.16

ocks

-0.16

gos

-0.15

hea

-0.15

fly

-0.15

rego

-0.14

iating

-0.14

/classes

-0.14

icon

-0.14

POSITIVE LOGITS

ants

0.25

ant

0.22

IONS

0.19

 victory

0.18

ibrate

0.17

ifornia

0.17

ibrated

0.17

aint

0.17

/assert

0.16

bers

0.15

Activations Density 0.029%

phrases related to legal claims and assertions

No Comments

No Known Activations