INDEX

Explanations

references to keynote presentations and speeches at events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lom

-0.16

 mastur

-0.15

pcodes

-0.14

rets

-0.14

omorphic

-0.14

esktop

-0.14

 Weather

-0.14

esub

-0.14

xCC

-0.14

 weather

-0.14

POSITIVE LOGITS

alt

0.16

ledge

0.15

Tel

0.15

 Strand

0.14

 Intr

0.14

TI

0.14

 superf

0.14

bsite

0.14

toJson

0.14

intr

0.14

Activations Density 0.002%

references to keynote presentations and speeches at events

No Comments

No Known Activations