INDEX

Explanations

terminologies related to conditions, requirements, or obligations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

/GPL

-0.17

arella

-0.17

.MixedReality

-0.16

.IsNullOr

-0.15

gow

-0.15

gli

-0.15

hangi

-0.15

polator

-0.14

/Gate

-0.14

POSITIVE LOGITS

is

0.16

no

0.15

 import

0.15

ATS

0.15

upe

0.14

 pocket

0.14

 Lawson

0.14

 Roberts

0.14

STM

0.14

Activations Density 0.004%

terminologies related to conditions, requirements, or obligations in various contexts

No Comments

No Known Activations