INDEX

Explanations

words related to legal issues and allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

plor

-0.16

enge

-0.16

/Branch

-0.16

verts

-0.15

bons

-0.15

studio

-0.15

ãĥªãĤ¹

-0.14

asic

-0.14

ITHER

-0.14

 Bond

-0.14

POSITIVE LOGITS

 trÃŃ

0.17

ayne

0.16

elled

0.14

 transparent

0.14

-transparent

0.14

uum

0.14

ãĥ¼ãĥį

0.14

-elected

0.14

udo

0.13

Activations Density 0.054%

words related to legal issues and allegations

No Comments

No Known Activations