INDEX

Explanations

words or phrases indicating size or magnitude

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

eling

-0.16

.CurrentRow

-0.15

ãĤĵãģ¨

-0.14

Äįel

-0.14

zon

-0.14

MethodInfo

-0.14

chant

-0.14

ousse

-0.14

-0.13

FIXME

-0.13

POSITIVE LOGITS

-scale

0.25

/big

0.20

-grand

0.18

oted

0.17

inning

0.17

spender

0.17

 number

0.16

 Ã¶lÃ§Ã¼de

0.16

uja

0.16

atsby

0.16

Activations Density 0.055%

words or phrases indicating size or magnitude

No Comments

No Known Activations