INDEX

Explanations

instances of specific years, particularly in the context of notable events

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

stru

-0.17

Ã©nÃ©

-0.16

akov

-0.16

akat

-0.16

@student

-0.15

ÑħÑĥ

-0.15

WEEN

-0.14

uggy

-0.14

uliar

-0.14

Ã©c

-0.14

POSITIVE LOGITS

ousel

0.17

RTC

0.15

canf

0.14

asn

0.14

gnore

0.14

EOF

0.14

asje

0.14

ardon

0.14

 consc

0.13

LOT

0.13

Activations Density 0.022%

instances of specific years, particularly in the context of notable events

No Comments

No Known Activations