INDEX

Explanations

phrases indicating duration or a sense of continuity over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pai

-0.17

tdown

-0.16

dge

-0.16

ikit

-0.15

cestor

-0.14

iversit

-0.14

oretical

-0.13

inson

-0.13

ffect

-0.13

 soon

-0.13

POSITIVE LOGITS

ago

0.41

 since

0.34

since

0.27

ingly

0.27

ago

0.26

Since

0.24

ed

0.23

 Since

0.23

-standing

0.23

Ago

0.22

Activations Density 0.017%

phrases indicating duration or a sense of continuity over time

No Comments

No Known Activations