INDEX

Explanations

technical terminology related to software and programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

éĲĺ

-0.15

oby

-0.14

 Abdul

-0.14

 Accessibility

-0.14

BUM

-0.14

à¥įà¤µà¤µ

-0.14

oz

-0.14

ocker

-0.14

Î³Î·

-0.13

verts

-0.13

POSITIVE LOGITS

0.18

0.16

0.15

0.14

 tÃŃch

0.13

cxx

0.13

.co

0.13

iena

0.13

Activations Density 0.017%

technical terminology related to software and programming languages

No Comments

No Known Activations