INDEX

Explanations

names and titles of individuals involved in legal contexts or proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

chner

-0.17

aiser

-0.16

ibar

-0.14

angan

-0.14

ÏİÎ½

-0.13

å±ħæ°ĳ

-0.13

 Northern

-0.13

chet

-0.13

riet

-0.13

POSITIVE LOGITS

zell

0.14

agnostics

0.14

elin

0.14

ornings

0.14

Elf

0.13

 Bender

0.13

 Bent

0.13

 Lindsay

0.13

atee

0.13

enburg

0.13

Activations Density 0.245%

names and titles of individuals involved in legal contexts or proceedings

No Comments

No Known Activations