INDEX

Explanations

attributes related to product features and performance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.scalablytyped

-0.15

.shell

-0.15

FormatException

-0.15

 setInput

-0.15

AAD

-0.15

 Razor

-0.14

sembler

-0.14

 shell

-0.14

elix

-0.14

lush

-0.14

POSITIVE LOGITS

ÙĬÙħØ©

0.15

 ç²¾

0.15

refs

0.15

Å¾it

0.14

/stdc

0.14

anya

0.14

Bj

0.14

Ã·

0.14

ãĥĹãĥª

0.14

_LIGHT

0.14

Activations Density 0.213%

attributes related to product features and performance

No Comments

No Known Activations