INDEX

Explanations

phrases related to time, dates, and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oron

-0.16

eneral

-0.16

oger

-0.16

alyzer

-0.15

 Ð²Ð·

-0.15

okane

-0.14

 cogn

-0.14

atz

-0.14

alink

-0.14

áº¿t

-0.14

POSITIVE LOGITS

inst

0.15

uv

0.14

 instinct

0.14

Ĵ

0.14

 Stanton

0.14

å¨ĺ

0.13

 Struct

0.13

ug

0.13

 subsid

0.13

ContentView

0.13

Activations Density 0.002%

phrases related to time, dates, and categorization

No Comments

No Known Activations