INDEX

Explanations

references to evaluations and decisions related to past experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.hh

-0.16

yx

-0.15

osi

-0.15

ÙĨØ³

-0.15

.scalablytyped

-0.14

ciÃ³n

-0.14

ensible

-0.14

ensch

-0.14

Fit

-0.13

 cannot

-0.13

POSITIVE LOGITS

 probably

0.38

 likely

0.34

probably

0.31

 Probably

0.31

Probably

0.31

 possibly

0.30

likely

0.30

 maybe

0.28

 perhaps

0.27

 Likely

0.26

Activations Density 0.172%

references to evaluations and decisions related to past experiences

No Comments

No Known Activations