INDEX

Explanations

topics related to trends, recommendations, and challenges in various areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ermal

-0.14

ota

-0.14

 skim

-0.14

BackStack

-0.14

 embar

-0.14

ju

-0.13

chant

-0.13

iselect

-0.13

POSITIVE LOGITS

jmu

0.15

 twins

0.15

ÏĦÎ±Î½

0.15

inite

0.15

aso

0.14

 dayan

0.14

oire

0.14

inish

0.14

.epam

0.13

Activations Density 0.577%

topics related to trends, recommendations, and challenges in various areas

No Comments

No Known Activations