INDEX

Explanations

references to national institutions or commissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.16

iman

-0.14

asset

-0.14

alley

-0.14

 Lens

-0.14

nock

-0.14

otti

-0.14

InstanceState

-0.14

 å½

-0.14

POSITIVE LOGITS

ãĥ³ãĥģ

0.17

-level

0.17

ebra

0.16

erea

0.16

elon

0.15

ãĥīãĥ«

0.15

anda

0.15

.EventHandler

0.15

-Level

0.14

Activations Density 0.038%

references to national institutions or commissions

No Comments

No Known Activations