INDEX

Explanations

names and terms related to Dutch surnames or individuals

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

ugar

-0.16

æľŃ

-0.16

SEQUENTIAL

-0.15

Ð·Ð°Ð±

-0.15

icz

-0.14

senal

-0.14

ABCDEFG

-0.14

_whitespace

-0.14

emente

-0.14

CLEAR

-0.14

POSITIVE LOGITS

stroy

0.16

ECT

0.15

ias

0.15

-INF

0.15

 Brig

0.15

ãģıãĤĮãģŁ

0.15

av

0.14

aster

0.13

aka

0.13

Activations Density 0.014%

names and terms related to Dutch surnames or individuals

No Comments

No Known Activations