INDEX

Explanations

phrases related to scoring or successful attempts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

CAPE

-0.17

å²³

-0.16

isle

-0.16

Ð»Ð¾Ð¹

-0.16

venir

-0.15

lew

-0.15

amide

-0.14

ÏģÎµ

-0.14

ello

-0.13

åŁº

-0.13

POSITIVE LOGITS

afort

0.16

acho

0.16

íĹĪ

0.15

NSK

0.15

 Gaul

0.14

urat

0.14

ichi

0.14

Woo

0.14

 sÃŃd

0.14

Activations Density 0.047%

phrases related to scoring or successful attempts in various contexts

No Comments

No Known Activations