INDEX

Explanations

references to large quantities of people or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

igham

-0.16

umed

-0.14

endants

-0.14

oningen

-0.14

ÑĢÐ°Ñħ

-0.13

adden

-0.13

ependency

-0.13

uned

-0.13

Enumerable

-0.13

nde

-0.13

POSITIVE LOGITS

of

0.22

azi

0.18

fold

0.17

 thousands

0.15

/all

0.15

-sided

0.15

-many

0.14

 hundreds

0.14

neau

0.14

uster

0.14

Activations Density 0.019%

references to large quantities of people or groups

No Comments

No Known Activations