INDEX

Explanations

instances of the reflexive verb "se" in various grammatical forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

zers

-0.17

cobra

-0.15

elib

-0.15

-0.14

asser

-0.14

rif

-0.14

affles

-0.14

à¸¡à¸Ń

-0.14

tes

-0.14

POSITIVE LOGITS

Vel

0.15

NEG

0.14

apiro

0.14

ĵn

0.14

bond

0.14

etus

0.14

esch

0.14

 permalink

0.14

oma

0.13

ikan

0.13

Activations Density 0.011%

instances of the reflexive verb "se" in various grammatical forms

No Comments

No Known Activations