INDEX

Explanations

references to high-quality products or services

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

laps

-0.17

akin

-0.15

vere

-0.15

ÚĺÙĩ

-0.15

bane

-0.14

&a

-0.14

 serious

-0.14

apr

-0.14

obao

-0.14

ìĭł

-0.13

POSITIVE LOGITS

0.15

entiful

0.14

anning

0.14

 counters

0.14

ofs

0.14

cion

0.14

OMET

0.14

á»¥c

0.14

ysi

0.14

Activations Density 0.012%

references to high-quality products or services

No Comments

No Known Activations