INDEX

Explanations

references to averages and average values in data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

_defaults

-0.16

ud

-0.16

elig

-0.16

unga

-0.16

pher

-0.15

enames

-0.15

vat

-0.14

avl

-0.14

oras

-0.14

isco

-0.14

POSITIVE LOGITS

joe

0.25

Joe

0.22

Joe

0.20

/std

0.18

-case

0.18

-sized

0.18

-priced

0.17

sac

0.17

bilt

0.16

/max

0.16

Activations Density 0.024%

references to averages and average values in data context

No Comments

No Known Activations