INDEX

Explanations

words related to emotional experiences and states

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

AES

-0.16

anoia

-0.15

ngth

-0.15

acin

-0.15

acio

-0.14

trieve

-0.14

ÙĨÛĮÙĨ

-0.14

alyzer

-0.14

_GL

-0.14

edn

-0.14

POSITIVE LOGITS

ruit

0.17

ogs

0.15

 maturity

0.15

 Nass

0.15

imb

0.15

0.14

ego

0.14

ycl

0.14

_calls

0.14

ful

0.14

Activations Density 0.021%

words related to emotional experiences and states

No Comments

No Known Activations