INDEX

Explanations

temporal phrases indicating durations or specific time frames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ONGO

-0.16

áº©u

-0.15

lue

-0.15

ulings

-0.15

enin

-0.15

Mej

-0.14

azor

-0.14

bah

-0.14

oS

-0.14

POSITIVE LOGITS

 time

0.17

ago

0.16

acam

0.16

apa

0.16

ago

0.16

 Pager

0.15

riba

0.15

ckill

0.15

ck

0.14

 intervals

0.14

Activations Density 0.062%

temporal phrases indicating durations or specific time frames

No Comments

No Known Activations