INDEX

Explanations

mentions of upcoming events or announcements

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

anus

-0.16

UGIN

-0.15

UGHT

-0.15

stan

-0.14

chten

-0.14

ught

-0.14

raya

-0.14

 tháº§u

-0.14

urv

-0.14

bao

-0.14

POSITIVE LOGITS

azel

0.17

0.15

ippets

0.15

ikh

0.14

rier

0.14

 Baths

0.14

asel

0.13

umerator

0.13

hone

0.13

 baths

0.13

Activations Density 0.012%

mentions of upcoming events or announcements

No Comments

No Known Activations