INDEX

Explanations

references to specific locations, events, or occurrences related to news and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

acet

-0.15

olo

-0.13

hod

-0.13

psz

-0.13

ematik

-0.13

æĪ

-0.13

_apps

-0.13

ifr

-0.13

 coer

-0.13

iten

-0.13

POSITIVE LOGITS

Tun

0.17

 ((__

0.16

udes

0.15

ison

0.14

 casc

0.14

 Nose

0.14

$class

0.14

oga

0.13

 Cant

0.13

ipp

0.13

Activations Density 1.757%

references to specific locations, events, or occurrences related to news and updates

No Comments

No Known Activations