INDEX

Explanations

variations of the word "Er" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

riv

-0.17

ened

-0.16

ariat

-0.16

oint

-0.15

croft

-0.15

pter

-0.15

arters

-0.15

ecko

-0.15

ez

-0.15

richt

-0.14

POSITIVE LOGITS

asmus

0.22

ector

0.20

antz

0.19

ECTOR

0.17

atz

0.16

oded

0.16

hythm

0.16

ichel

0.15

ugin

0.15

ude

0.15

Activations Density 0.011%

variations of the word "Er" in different contexts

No Comments

No Known Activations