INDEX

Explanations

names or references to individuals, particularly those involving the name "Lyn" or its variations

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

ago

-0.17

à¸ĵ

-0.14

UGHT

-0.14

 æĿ

-0.14

strain

-0.14

aney

-0.14

ermann

-0.14

AGON

-0.14

china

-0.14

 EÅŁ

-0.13

POSITIVE LOGITS

enne

0.20

0.19

ewis

0.17

nda

0.17

hoa

0.16

soever

0.15

hoe

0.15

asma

0.15

ild

0.15

ierz

0.15

Activations Density 0.017%

names or references to individuals, particularly those involving the name "Lyn" or its variations

No Comments

No Known Activations