INDEX

Explanations

linguistic patterns and syntactic structures within textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Residence

-0.15

¬ģ

-0.15

cel

-0.14

 residence

-0.14

he

-0.14

ÙĪØ§Øª

-0.13

 kontakte

-0.13

Ð»Ð¾Ñĩ

-0.13

èĻŁ

-0.13

 Locker

-0.13

POSITIVE LOGITS

 Horton

0.16

dum

0.16

PointerType

0.15

Ð°ÑĤÐ¾

0.15

ards

0.14

Ã¤tt

0.14

orna

0.14

agnost

0.14

Dro

0.14

orta

0.14

Activations Density 0.008%

linguistic patterns and syntactic structures within textual content

No Comments

No Known Activations