INDEX

Explanations

negative constructs and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

paired

-0.16

rop

-0.15

Ace

-0.15

ahan

-0.14

.gdx

-0.14

ÏĬ

-0.14

nth

-0.14

Ace

-0.14

antu

-0.14

POSITIVE LOGITS

igon

0.21

bst

0.19

DT

0.18

 konkrÃ©t

0.15

ursal

0.15

ITTE

0.15

ISTA

0.15

kus

0.14

ÑĢÐ¾Ð½

0.14

 Giang

0.13

Activations Density 0.001%

negative constructs and legal terminology

No Comments

No Known Activations

negative constructs and legal terminology

No Comments

No Known Activations