INDEX

Explanations

instances of significant numerical or quantifiable concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

onda

-0.14

chg

-0.14

aket

-0.14

icari

-0.14

 Specification

-0.14

unda

-0.14

vÄĽt

-0.14

odic

-0.14

ovol

-0.13

POSITIVE LOGITS

'gc

0.17

ENA

0.14

Ä°Åŀ

0.13

Deg

0.13

 this

0.13

lexport

0.13

.Dev

0.13

 Ø§ÙĦØ¬ÙĨ

0.13

@js

0.13

aghan

0.13

Activations Density 0.000%

instances of significant numerical or quantifiable concepts

No Comments

No Known Activations