INDEX

Explanations

phrases and structures indicative of storytelling or narrative elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ethylene

-0.16

iba

-0.15

ari

-0.15

aris

-0.15

 Alexand

-0.14

ade

-0.14

ager

-0.14

.utf

-0.14

awai

-0.14

aggi

-0.14

POSITIVE LOGITS

_EXTRA

0.15

ÑĨÑı

0.15

-fw

0.15

Lod

0.14

orro

0.14

inel

0.14

akra

0.14

istrovstvÃŃ

0.14

¹

0.14

isRequired

0.14

Activations Density 0.229%

phrases and structures indicative of storytelling or narrative elements

No Comments

No Known Activations