INDEX

Explanations

proper names and titles

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

 addCriterion

-0.19

raÅ¾

-0.18

itage

-0.16

iae

-0.16

ayette

-0.15

.AttributeSet

-0.14

peria

-0.14

emme

-0.14

ohana

-0.14

adier

-0.14

POSITIVE LOGITS

ypo

0.18

 Dynam

0.16

0.15

 Tight

0.15

wahl

0.15

yp

0.14

owski

0.14

etheus

0.14

iggins

0.14

Activations Density 0.161%

proper names and titles

No Comments

No Known Activations