INDEX

Explanations

occurrences of the word "point" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

æĸ¹éĿ¢

-0.16

obs

-0.16

esa

-0.15

elp

-0.14

env

-0.14

Å¡i

-0.14

 attendance

-0.14

ndo

-0.14

ednou

-0.13

Ã¶g

-0.13

POSITIVE LOGITS

punkt

0.22

pcf

0.20

atos

0.19

idl

0.15

 Suff

0.15

aines

0.14

.stage

0.14

ÙĪØ¯ÛĮ

0.14

ekl

0.14

punk

0.14

Activations Density 0.047%

occurrences of the word "point" and its variations

No Comments

No Known Activations