INDEX

Explanations

terms related to legal professions and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

agu

-0.15

ÑıÐ±

-0.15

.opend

-0.15

DTV

-0.14

apos

-0.14

pur

-0.14

ierre

-0.14

 nhau

-0.14

osit

-0.14

acos

-0.14

POSITIVE LOGITS

0.15

 Porn

0.15

åĬ¡

0.15

porn

0.15

ÙĬÙĦØ§

0.14

å¾Ĵ

0.14

.hy

0.14

ÙĤÙħ

0.14

female

0.14

 Lawyer

0.14

Activations Density 0.001%

terms related to legal professions and experience

No Comments

No Known Activations