INDEX

Explanations

temporal references within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

urse

-0.17

chts

-0.15

dont

-0.14

 PureComponent

-0.14

onte

-0.14

ÅĪ

-0.14

Ð¾Ð»Ñĸ

-0.14

ãģĮãģĦ

-0.14

ouz

-0.14

uty

-0.13

POSITIVE LOGITS

 there

0.19

ceptor

0.15

soever

0.14

éļĽ

0.14

it

0.14

 they

0.14

immel

0.13

Ø¨Ø§Øª

0.13

rep

0.13

Activations Density 0.188%

temporal references within a narrative context

No Comments

No Known Activations