INDEX

Explanations

references to the name "Lore" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

LT

-0.15

ey

-0.15

ew

-0.15

emey

-0.15

ppers

-0.15

izer

-0.15

acker

-0.14

ayload

-0.14

 orbit

-0.14

ilib

-0.14

POSITIVE LOGITS

 Ipsum

0.21

angep

0.17

chestra

0.17

ENTE

0.17

iginal

0.17

 ipsum

0.16

idente

0.16

lus

0.15

IGIN

0.15

phe

0.15

Activations Density 0.030%

references to the name "Lore" and its variations in different contexts

No Comments

No Known Activations