INDEX

Explanations

articles and possessive pronouns indicating ownership or specificity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ElementsBy

-0.16

asl

-0.15

iest

-0.15

à¥ĭà¤¹

-0.14

oste

-0.14

-elements

-0.14

RIA

-0.14

_CHK

-0.14

Elements

-0.14

 element

-0.14

POSITIVE LOGITS

enko

0.18

 Morm

0.16

ortal

0.15

Ħĸ

0.15

pa

0.14

ÙĪÙĨØ§

0.14

 Fairfax

0.13

bw

0.13

bildung

0.13

enen

0.13

Activations Density 0.049%

articles and possessive pronouns indicating ownership or specificity

No Comments

No Known Activations