INDEX

Explanations

references to objects, especially photographs and significant moments or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ive

-0.16

ione

-0.15

LLU

-0.15

 Suche

-0.15

ube

-0.15

anine

-0.14

 MÃ¶glichkeit

-0.14

ãģ¨ãģĵãĤį

-0.14

 touches

-0.14

 Familie

-0.14

POSITIVE LOGITS

 Pendant

0.21

auge

0.20

 Schema

0.19

ritis

0.19

 Datum

0.18

 Ensemble

0.18

Fmt

0.17

 Stadium

0.17

chema

0.17

 Unternehmen

0.17

Activations Density 0.031%

references to objects, especially photographs and significant moments or events

No Comments

No Known Activations