INDEX

Explanations

elements that discuss storytelling and narrative structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ery

-0.23

/bus

-0.16

ï¸ı

-0.15

----</

-0.15

TION

-0.15

ders

-0.15

alf

-0.15

ullen

-0.15

ick

-0.15

sy

-0.15

POSITIVE LOGITS

/story

0.20

arc

0.18

-driven

0.17

 told

0.17

ative

0.17

/Instruction

0.16

atively

0.16

 structure

0.16

 arcs

0.16

_voice

0.15

Activations Density 0.010%

elements that discuss storytelling and narrative structure

No Comments

No Known Activations