INDEX

Explanations

phrases indicating possession or existence 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 @ 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

no

-0.15

OnInit

-0.15

inho

-0.14

ilate

-0.14

 only

-0.14

_already

-0.14

ander

-0.14

uelle

-0.14

una

-0.13

ichert

-0.13

POSITIVE LOGITS

 indeed

0.18

 occasionally

0.16

 Indeed

0.15

 SOME

0.15

 however

0.15

inde

0.15

 somewhat

0.15

iform

0.14

 some

0.14

Activations Density 0.062%

phrases indicating possession or existence in various contexts

No Comments

No Known Activations