INDEX

Explanations

words and phrases related to rebooting or reviving stories in entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

erot

-0.15

 Prairie

-0.15

æĶ

-0.14

lain

-0.14

åĸ

-0.14

IBE

-0.14

ANGO

-0.14

otch

-0.13

IVO

-0.13

itage

-0.13

POSITIVE LOGITS

ptrdiff

0.17

	TokenName

0.17

/print

0.16

é¾

0.16

alone

0.15

Dump

0.15

 Boiler

0.14

ollo

0.14

sla

0.14

 slime

0.14

Activations Density 0.297%

words and phrases related to rebooting or reviving stories in entertainment

No Comments

No Known Activations