INDEX

Explanations

phrases indicating a central location or context within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

è¼ª

-0.16

antu

-0.15

 DÃ¼n

-0.15

 Exped

-0.15

yro

-0.14

idos

-0.14

anth

-0.14

.VideoCapture

-0.14

folio

-0.14

andy

-0.14

POSITIVE LOGITS

uria

0.15

 Rath

0.15

.heroku

0.15

 ongoing

0.14

ico

0.14

punkt

0.14

 Core

0.14

/right

0.14

Activations Density 0.019%

phrases indicating a central location or context within a narrative

No Comments

No Known Activations