INDEX

Explanations

concepts related to praise and recognition from a higher authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

hei

-0.18

_PROVID

-0.17

liqu

-0.15

elig

-0.15

bei

-0.14

emouth

-0.14

hey

-0.14

reh

-0.14

modo

-0.14

eldom

-0.14

POSITIVE LOGITS

cad

0.15

-Compatible

0.14

pyx

0.14

IOD

0.14

è¼ī

0.14

ÙĦØª

0.13

_nth

0.13

 vulgar

0.13

 hyster

0.13

ÂĤ

0.13

Activations Density 0.480%

concepts related to praise and recognition from a higher authority

No Comments

No Known Activations