INDEX

Explanations

code structures and syntax elements

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

forcer

-0.15

à¸Ĭ

-0.14

 soph

-0.14

SingleOrDefault

-0.14

eenth

-0.14

Ã¢y

-0.14

rypton

-0.14

efined

-0.14

ings

-0.13

faces

-0.13

POSITIVE LOGITS

utos

0.17

rome

0.15

oyer

0.15

ayette

0.15

kÃ³w

0.15

angel

0.14

endale

0.14

tte

0.14

 Khal

0.14

CTSTR

0.14

Activations Density 0.018%

code structures and syntax elements

No Comments

No Known Activations