INDEX

Explanations

the mention of "Hills" in relation to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ìķ¼

-0.17

zone

-0.15

ailability

-0.14

ãĥ¼ãĥł

-0.14

Rut

-0.14

ãĥ³ãĤ¹

-0.14

huz

-0.14

 Grad

-0.14

coln

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.17

Ø¬Ø§ÙĨ

0.14

ulfilled

0.14

osphere

0.14

uppies

0.14

barang

0.14

à¤ĺ

0.14

.micro

0.14

Verdana

0.13

 Ø§ÙĦØ¥ÙĨ

0.13

Activations Density 0.004%

the mention of "Hills" in relation to various contexts

No Comments

No Known Activations