INDEX

Explanations

phrases indicating customization or tailoring to specific needs

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

YG

-0.16

 dikke

-0.16

SDL

-0.15

emoc

-0.15

Zem

-0.14

spo

-0.14

 Cyrus

-0.14

Äįem

-0.14

Pam

-0.14

rika

-0.13

POSITIVE LOGITS

elsen

0.16

etter

0.15

 Karlov

0.14

LinkId

0.14

mach

0.14

otta

0.14

fab

0.14

 Barnett

0.14

-Ray

0.13

Activations Density 0.026%

phrases indicating customization or tailoring to specific needs

No Comments

No Known Activations