INDEX

Explanations

occurrences of the word "arr" in various contexts and its derivatives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enk

-0.17

PCA

-0.16

ovice

-0.16

iens

-0.15

ippets

-0.15

èħ°

-0.15

Ø®Ø§ÙĨÙĩ

-0.14

uess

-0.14

_SYM

-0.14

AXB

-0.14

POSITIVE LOGITS

hythm

0.35

angement

0.34

anged

0.31

iving

0.30

ivals

0.30

aign

0.30

anging

0.27

hyth

0.25

ond

0.24

anger

0.24

Activations Density 0.006%

occurrences of the word "arr" in various contexts and its derivatives

No Comments

No Known Activations