INDEX

Explanations

variations of the word "progress" and its associated concepts, often in a socio-political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

indow

-0.17

ndon

-0.17

unami

-0.15

icina

-0.15

ITY

-0.15

ikel

-0.15

pais

-0.14

-ci

-0.14

.defer

-0.14

THON

-0.14

POSITIVE LOGITS

ional

0.30

ions

0.29

ively

0.28

ivism

0.28

ion

0.26

sing

0.24

ive

0.21

ives

0.21

iveness

0.21

ses

0.20

Activations Density 0.020%

variations of the word "progress" and its associated concepts, often in a socio-political context

No Comments

No Known Activations