INDEX

Explanations

references to television shows and their hosts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olith

-0.16

ibu

-0.15

Ã©ri

-0.15

xit

-0.14

.enterprise

-0.14

apk

-0.14

iap

-0.13

Narrated

-0.13

biz

-0.13

itler

-0.13

POSITIVE LOGITS

 ActiveForm

0.16

Jay

0.15

ÙĴØ³

0.14

AGMA

0.14

agini

0.14

_widgets

0.14

 Ø§Ø«

0.14

AZY

0.14

XE

0.14

Coy

0.13

Activations Density 0.087%

references to television shows and their hosts

No Comments

No Known Activations