INDEX

Explanations

occurrences of the word "end" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Specifies

-0.15

AILABLE

-0.15

adb

-0.15

agus

-0.15

-0.14

.cfg

-0.14

ounce

-0.14

adows

-0.13

quil

-0.13

POSITIVE LOGITS

/end

0.26

end

0.25

orses

0.23

End

0.23

ogenous

0.23

urance

0.22

orse

0.22

earing

0.22

=end

0.22

,end

0.21

Activations Density 0.030%

occurrences of the word "end" and its variations

No Comments

No Known Activations