INDEX

Explanations

concepts related to information sharing and collaboration across different parties or agencies

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

 åľŁ

-0.17

aso

-0.15

ubby

-0.15

forced

-0.15

UBY

-0.15

ombat

-0.15

roulette

-0.15

tabpanel

-0.15

ledi

-0.14

LOC

-0.14

POSITIVE LOGITS

 across

0.20

oire

0.18

 crossing

0.18

an

0.18

 Across

0.17

 Crossing

0.17

Across

0.16

Cross

0.16

_cross

0.16

Activations Density 0.156%

concepts related to information sharing and collaboration across different parties or agencies

No Comments

No Known Activations