INDEX

Explanations

phrases that indicate conditions or situations related to change or development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Éµ

-0.16

indo

-0.15

ouro

-0.15

ewart

-0.14

conds

-0.13

igest

-0.13

stitute

-0.13

orners

-0.13

ufen

-0.13

aska

-0.13

POSITIVE LOGITS

arken

0.17

isine

0.17

beck

0.15

 mere

0.15

istrovstvÃŃ

0.15

addock

0.14

robat

0.14

ebek

0.14

attice

0.13

usan

0.13

Activations Density 0.146%

phrases that indicate conditions or situations related to change or development

No Comments

No Known Activations