INDEX

Explanations

locations, particularly cities and regions

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

-0.16

kid

-0.14

anders

-0.14

anded

-0.14

isa

-0.14

aj

-0.13

ORIES

-0.13

ORED

-0.13

esta

-0.13

fait

-0.13

POSITIVE LOGITS

Ã½t

0.18

ragen

0.16

umen

0.16

 Virt

0.15

ChangedEventArgs

0.14

ickle

0.14

unei

0.14

_usec

0.14

/use

0.14

umo

0.14

Activations Density 0.101%

locations, particularly cities and regions

No Comments

No Known Activations