INDEX

Explanations

references to the Soviet Union and its historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ã¡d

-0.14

idar

-0.14

Ð½Ð¾Ð²Ð¸Ð´

-0.14

ãĥŃãĥ¼

-0.14

ERING

-0.14

 Tory

-0.14

inspace

-0.13

Ø§ÙĤØ©

-0.13

fec

-0.13

ein

-0.13

POSITIVE LOGITS

ischer

0.15

0.14

 earth

0.14

 Kaynak

0.14

raid

0.14

0.13

 grown

0.13

ä½ľ

0.13

/free

0.13

CELL

0.13

Activations Density 0.028%

references to the Soviet Union and its historical context

No Comments

No Known Activations