INDEX

Explanations

instances of personal experiences and opinions related to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 ifndef

-0.15

uros

-0.13

æĹıèĩªæ²»

-0.13

ancode

-0.13

erland

-0.13

tran

-0.13

ncy

-0.12

loadModel

-0.12

quential

-0.12

Ð»ÑİÐ±

-0.12

POSITIVE LOGITS

SD

0.13

hal

0.13

0.12

 merk

0.12

 Bust

0.12

dk

0.12

UBLE

0.12

ADDE

0.12

interop

0.12

HAM

0.12

Activations Density 1.755%

instances of personal experiences and opinions related to services or products

No Comments

No Known Activations