INDEX

Explanations

features related to welcoming or inviting elements in a space

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

infra

-0.16

 infr

-0.16

 infra

-0.16

INF

-0.14

 bunk

-0.14

áº¥c

-0.14

©

-0.14

dlg

-0.13

oltip

-0.13

 onboard

-0.13

POSITIVE LOGITS

 entrance

0.48

 entry

0.44

 Entrance

0.42

 Entry

0.40

entry

0.39

 entrances

0.39

entr

0.38

Entry

0.35

 front

0.35

 entrada

0.35

Activations Density 0.166%

features related to welcoming or inviting elements in a space

No Comments

No Known Activations