INDEX

Explanations

prepositions indicating location or involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ota

-0.16

gaard

-0.15

éĥİ

-0.15

okin

-0.15

gc

-0.14

ALIGN

-0.14

adera

-0.14

onaut

-0.14

GC

-0.14

POSITIVE LOGITS

imuth

0.15

oplay

0.15

ãģķãģĦ

0.14

ezi

0.14

 Richt

0.14

_encoded

0.14

ddb

0.13

.pivot

0.13

 Genesis

0.13

Ã¡tek

0.13

Activations Density 0.196%

prepositions indicating location or involvement

No Comments

No Known Activations