INDEX

Explanations

forms of the verb "to be" and its derivatives 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 @ 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

arges

-0.19

CHASE

-0.16

.Generated

-0.14

apan

-0.14

oot

-0.13

ëľ

-0.13

tym

-0.13

 gang

-0.13

upt

-0.13

sch

-0.13

POSITIVE LOGITS

rief

0.14

CEEDED

0.14

 canh

0.14

jez

0.14

wayne

0.14

jsc

0.14

edl

0.14

iedy

0.13

utor

0.13

 Cindy

0.13

Activations Density 0.083%

forms of the verb "to be" and its derivatives in various contexts

No Comments

No Known Activations