INDEX

Explanations

programming-related syntax and structure, particularly focusing on method calls and collection operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

kul

-0.17

 Matth

-0.14

oot

-0.14

rÃ¡l

-0.13

ibus

-0.13

_SPELL

-0.13

Latch

-0.13

/dev

-0.13

ansa

-0.13

Tech

-0.13

POSITIVE LOGITS

hetto

0.17

.dateTime

0.16

olu

0.15

inae

0.15

ÐµÑĢÐµÑĩ

0.15

Ĳľ

0.14

enthal

0.14

oro

0.14

ãģĮãģĦ

0.14

Activations Density 0.019%

programming-related syntax and structure, particularly focusing on method calls and collection operations

No Comments

No Known Activations