INDEX

Explanations

terms related to academic and scientific discourse, particularly focused on research and its contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lsen

-0.15

ovice

-0.15

,:,

-0.14

 ordinary

-0.14

 fram

-0.14

à¹ĥà¸Ī

-0.13

reuse

-0.13

use

-0.13

 suche

-0.13

UX

-0.13

POSITIVE LOGITS

ocket

0.16

eco

0.15

chest

0.15

ï»¿#

0.15

ymb

0.14

Ð»ÑĥÐ³

0.14

ingt

0.14

ala

0.14

creat

0.14

gow

0.14

Activations Density 0.073%

terms related to academic and scientific discourse, particularly focused on research and its contributions

No Comments

No Known Activations