INDEX

Explanations

mentions of lawyers and legal professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

wald

-0.18

opal

-0.16

placer

-0.16

 priv

-0.15

outu

-0.15

okedex

-0.15

avic

-0.14

priv

-0.14

uib

-0.14

lere

-0.14

POSITIVE LOGITS

ocket

0.18

hin

0.15

/legal

0.15

qed

0.14

bidden

0.14

ading

0.14

rgan

0.14

ä»ĺãģĳ

0.14

ivec

0.14

ize

0.13

Activations Density 0.005%

mentions of lawyers and legal professionals

No Comments

No Known Activations