INDEX

Explanations

phrases related to specific viewpoints or perspectives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 ?><?

-0.15

åłĤ

-0.15

ouis

-0.15

ÙĩØ§Ø±

-0.14

\Backend

-0.14

ancias

-0.14

SYM

-0.14

eday

-0.14

ubat

-0.14

isten

-0.14

POSITIVE LOGITS

 view

0.70

view

0.60

 View

0.53

 viewpoint

0.52

-view

0.51

View

0.50

_view

0.47

 VIEW

0.46

 viewed

0.46

.view

0.44

Activations Density 0.025%

phrases related to specific viewpoints or perspectives in various contexts

No Comments

No Known Activations