INDEX

Explanations

negative sentiment or criticism towards movies and their production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ittest

-0.16

NEL

-0.15

okit

-0.15

amina

-0.15

andon

-0.13

urb

-0.13

 fierc

-0.13

iams

-0.13

CRET

-0.13

ANE

-0.13

POSITIVE LOGITS

onium

0.17

RTC

0.15

.descriptor

0.14

IRR

0.14

esz

0.14

grpc

0.14

_rwlock

0.14

efon

0.14

retch

0.13

idor

0.13

Activations Density 0.629%

negative sentiment or criticism towards movies and their production

No Comments

No Known Activations

negative sentiment or criticism towards movies and their production

No Comments

No Known Activations