INDEX

Explanations

expressions of strong emotions or exclamations

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

ezier

-0.16

iland

-0.16

Ð¾Ð¿Ð°Ñģ

-0.15

eree

-0.15

EMPLARY

-0.15

onders

-0.15

gend

-0.15

akin

-0.14

unsch

-0.14

BASH

-0.14

POSITIVE LOGITS

obe

0.16

0.14

RefreshLayout

0.14

ally

0.14

0.13

odie

0.13

Interpreter

0.13

 shame

0.13

Activations Density 0.222%

expressions of strong emotions or exclamations

No Comments

No Known Activations