INDEX

Explanations

phrases indicating a critical or evaluative perspective on films

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

 sÃ¡t

-0.15

erset

-0.15

asco

-0.14

_rq

-0.14

Seriously

-0.14

omor

-0.14

LAP

-0.14

ovu

-0.14

æĬľ

-0.14

retim

-0.13

POSITIVE LOGITS

 decent

0.25

OK

0.17

 nicely

0.17

ok

0.16

 okay

0.16

iler

0.16

nic

0.15

 redeem

0.15

 nice

0.15

basic

0.15

Activations Density 0.290%

phrases indicating a critical or evaluative perspective on films

No Comments

No Known Activations