INDEX

Explanations

prepositions or words indicating relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

illas

-0.16

spiel

-0.16

Ã³wn

-0.16

UFF

-0.15

 Cres

-0.15

uff

-0.14

estate

-0.14

bs

-0.14

yll

-0.14

POSITIVE LOGITS

stÃ¼t

0.17

ird

0.17

neh

0.16

GROUND

0.16

nehmer

0.15

erosis

0.15

tps

0.15

legs

0.15

ein

0.15

ESA

0.14

Activations Density 0.008%

prepositions or words indicating relationships and connections

No Comments

No Known Activations