INDEX

Explanations

punctuations and their surrounding contextual phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

deps

-0.15

olvers

-0.15

InView

-0.15

uling

-0.14

orman

-0.14

alla

-0.14

oi

-0.14

ixin

-0.13

POSITIVE LOGITS

 everything

0.21

everything

0.20

 Everything

0.20

Everything

0.20

 things

0.17

traction

0.16

 NOTHING

0.15

 Things

0.15

 temperatures

0.15

 tudo

0.15

Activations Density 0.019%

punctuations and their surrounding contextual phrases

No Comments

No Known Activations