INDEX

Explanations

words related to hospitality and accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.18

alach

-0.16

alom

-0.15

ity

-0.15

ÑĢÐ°Ð±Ð¾ÑĤ

-0.15

auga

-0.15

orrar

-0.14

chied

-0.14

POSITIVE LOGITS

lahoma

0.16

avad

0.16

liqu

0.15

ded

0.15

ses

0.15

sn

0.15

TECTED

0.14

zyst

0.14

 Logical

0.14

PackageManager

0.14

Activations Density 0.084%

words related to hospitality and accommodations

No Comments

No Known Activations