INDEX

Explanations

references to the television show "Saturday Night Live"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.17

 rein

-0.16

 Nicholas

-0.16

MX

-0.15

arro

-0.15

 Nagar

-0.15

éļİ

-0.15

ÙĨØ§ÙĨ

-0.14

Jur

-0.14

insk

-0.14

POSITIVE LOGITS

ãĥ¬ãĥ³

0.18

uter

0.17

lage

0.15

ITTER

0.15

ato

0.15

 addCriterion

0.15

PropertyValue

0.15

ld

0.14

elli

0.14

¢åįķ

0.14

Activations Density 0.026%

references to the television show "Saturday Night Live"

No Comments

No Known Activations