INDEX

Explanations

proper nouns, particularly names and specific places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

antha

-0.15

acro

-0.15

owski

-0.15

sos

-0.14

weed

-0.14

pars

-0.14

mainwindow

-0.14

-fi

-0.14

Ø±ÙĪØ´

-0.14

 eskort

-0.13

POSITIVE LOGITS

à¥ĩà¤¯

0.16

 weather

0.15

trap

0.14

 Collapse

0.14

0.13

emin

0.13

eteria

0.13

 fragile

0.13

ustain

0.13

Ø§Ø²Ùħ

0.13

Activations Density 0.108%

proper nouns, particularly names and specific places

No Comments

No Known Activations