INDEX

Explanations

prefixes and suffixes that imply actions or states related to activities and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

jit

-0.15

ipeg

-0.14

plier

-0.14

cpf

-0.14

AREST

-0.14

Éµ

-0.14

elix

-0.13

ÐµÐ»

-0.13

encia

-0.13

#endregion

-0.13

POSITIVE LOGITS

ollo

0.18

PCP

0.14

ab

0.14

Twe

0.14

.sections

0.14

ç»ĩ

0.14

big

0.14

finity

0.14

 hall

0.13

 pass

0.13

Activations Density 0.402%

prefixes and suffixes that imply actions or states related to activities and services

No Comments

No Known Activations