INDEX

Explanations

words and phrases related to entertainment and pop culture references

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

undry

-0.15

aha

-0.15

iesz

-0.14

 peter

-0.14

adro

-0.14

anton

-0.14

.LENGTH

-0.14

uso

-0.14

 smarty

-0.13

Ð·Ð½Ð°

-0.13

POSITIVE LOGITS

peed

0.15

/cms

0.14

orte

0.14

 mine

0.14

ÙĪØ±Ùĩ

0.13

inous

0.13

 trailer

0.13

 CACHE

0.13

.dds

0.13

Activations Density 0.331%

words and phrases related to entertainment and pop culture references

No Comments

No Known Activations