INDEX

Explanations

references to ecological or environmental topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ropol

-0.17

-0.16

 Nest

-0.15

jad

-0.15

èº«

-0.14

 Farmers

-0.14

ov

-0.13

 Gener

-0.13

ublished

-0.13

POSITIVE LOGITS

 morph

0.16

adir

0.16

ãĥĥãĥģ

0.15

 transition

0.15

eÄį

0.15

 underst

0.15

 Managed

0.15

unce

0.15

ayar

0.15

Transition

0.14

Activations Density 0.040%

references to ecological or environmental topics

No Comments

No Known Activations