INDEX

Explanations

dates and numerical indicators of time events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rub

-0.17

 special

-0.17

-0.15

bit

-0.15

 base

-0.15

Æ°

-0.15

ainer

-0.15

urch

-0.14

ump

-0.14

utter

-0.14

POSITIVE LOGITS

 showc

0.17

Äįan

0.16

ityEngine

0.16

ermen

0.15

TestFixture

0.15

-Ta

0.15

Charsets

0.15

/Core

0.15

 CActive

0.15

zza

0.15

Activations Density 0.065%

dates and numerical indicators of time events

No Comments

No Known Activations