INDEX

Explanations

abbreviations or acronyms related to technology or engineering

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bu

-0.17

 Bureau

-0.17

acier

-0.16

 Kerr

-0.16

 bureau

-0.16

azine

-0.16

bu

-0.15

adies

-0.14

iki

-0.14

bul

-0.14

POSITIVE LOGITS

Ãºc

0.15

OrFail

0.14

ienes

0.14

IGO

0.14

trigger

0.14

ivalent

0.13

Quad

0.13

tcb

0.13

oss

0.13

roit

0.13

Activations Density 0.009%

abbreviations or acronyms related to technology or engineering

No Comments

No Known Activations