INDEX

Explanations

elements related to technical or academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

avin

-0.15

rego

-0.14

 Tham

-0.14

zend

-0.14

ungi

-0.14

haft

-0.14

 Silent

-0.13

adium

-0.13

 criteria

-0.13

 Principle

-0.13

POSITIVE LOGITS

.ManyToMany

0.16

ForRow

0.15

CLUDING

0.15

MASK

0.15

BitFields

0.14

owi

0.14

DisplayStyle

0.14

YPE

0.14

 lesbi

0.14

autoreleasepool

0.14

Activations Density 0.001%

elements related to technical or academic references

No Comments

No Known Activations