INDEX

Explanations

references to the political discourse surrounding education and public policy

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

eg

-0.15

ÑĬ

-0.14

 toll

-0.14

hle

-0.14

UNU

-0.13

modes

-0.13

ces

-0.13

cut

-0.13

_EVAL

-0.13

room

-0.13

POSITIVE LOGITS

itus

0.19

-prepend

0.18

çıł

0.17

icz

0.15

áº¿

0.14

antom

0.14

arro

0.14

 dá»¥

0.14

antas

0.14

idelberg

0.14

Activations Density 0.263%

references to the political discourse surrounding education and public policy

No Comments

No Known Activations