INDEX

Explanations

references to educational levels, particularly secondary education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

defgroup

-0.16

Ø²Ùĩ

-0.15

ulan

-0.15

TEGER

-0.15

-gap

-0.14

usk

-0.14

uhn

-0.14

liness

-0.14

czy

-0.14

ableView

-0.13

POSITIVE LOGITS

-secondary

0.34

 Secondary

0.25

Secondary

0.24

secondary

0.23

 secondary

0.23

-level

0.21

arily

0.21

iliary

0.18

/high

0.18

.secondary

0.17

Activations Density 0.008%

references to educational levels, particularly secondary education

No Comments

No Known Activations

references to educational levels, particularly secondary education

No Comments

No Known Activations