INDEX

Explanations

references to characters and their relationships 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 @ 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

aeper

-0.16

ungi

-0.14

izr

-0.14

 ÑģÐ¸

-0.14

ÅĽnie

-0.14

ibri

-0.14

 ëĬ

-0.14

ark

-0.13

illis

-0.13

POSITIVE LOGITS

 whom

0.39

who

0.24

 whose

0.24

who

0.18

 introdu

0.18

whose

0.17

 Ø§ÙĦØ°ÙĬÙĨ

0.16

 kteÅĻÃŃ

0.15

ixe

0.14

ä»¬

0.14

Activations Density 0.711%

references to characters and their relationships in narratives

No Comments

No Known Activations