INDEX

Explanations

phrases related to the plot and storyline in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

utin

-0.16

á»Ńa

-0.15

suite

-0.15

zu

-0.15

abler

-0.15

yne

-0.15

 suite

-0.14

ÃŃas

-0.14

bak

-0.14

iences

-0.14

POSITIVE LOGITS

 binary

0.15

iones

0.14

itar

0.14

ÑĢÐ´

0.14

binary

0.14

 edge

0.14

knife

0.13

 Dwight

0.13

IRO

0.13

apse

0.13

Activations Density 0.005%

phrases related to the plot and storyline in narratives

No Comments

No Known Activations