INDEX

Explanations

entities and attributes related to cooperative gameplay and organizational aspects of events or classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

UMP

-0.16

antha

-0.15

umas

-0.14

yme

-0.14

yar

-0.14

-out

-0.14

-over

-0.13

lland

-0.13

POSITIVE LOGITS

up

0.87

 upto

0.69

up

0.47

(up

0.46

_up

0.45

Up

0.44

 lÃªn

0.43

Up

0.43

upt

0.41

.up

0.40

Activations Density 0.393%

entities and attributes related to cooperative gameplay and organizational aspects of events or classes

No Comments

No Known Activations